MiniCPM-Embedding
40.1K
248
2 languages
—
by
openbmb
Embedding Model
OTHER
Fair
40K downloads
Community-tested
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary
MiniCPM-Embedding 是面壁智能与清华大学自然语言处理实验室（THUNLP）、东北大学信息检索小组（NEUIR）共同开发的中英双语言文本嵌入模型，有如下特点： - 出色的中文、英文检索能力。 - 出色的中英跨语言检索能力。 MiniCPM-Embedding 基于 MiniCPM-2B-sft-bf16...
Code Examples
使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}使用方法 Usagetext
Instruction: {{ instruction }} Query: {{ query }}输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？输入格式 Input Formattext
Instruction: 为这个医学问题检索相关回答。Query: 咽喉癌的成因是什么？text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.text
Instruction: Given a claim about climate change, retrieve documents that support or refute the claim. Query: However the warming trend is slower than most climate models have forecast.环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]]环境要求 Requirementspythontransformers
from transformers import AutoModel, AutoTokenizer
import torch
import torch.nn.functional as F
model_name = "openbmb/MiniCPM-Embedding"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.float16).to("cuda")
# You can also use the following line to enable the Flash Attention 2 implementation
# model = AutoModel.from_pretrained(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", torch_dtype=torch.float16).to("cuda")
model.eval()
# 由于在 `model.forward` 中缩放了最终隐层表示，此处的 mean pooling 实际上起到了 weighted mean pooling 的作用
# As we scale hidden states in `model.forward`, mean pooling here actually works as weighted mean pooling
def mean_pooling(hidden, attention_mask):
s = torch.sum(hidden * attention_mask.unsqueeze(-1).float(), dim=1)
d = attention_mask.sum(dim=1, keepdim=True).float()
reps = s / d
return reps
@torch.no_grad()
def encode(input_texts):
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt', return_attention_mask=True).to("cuda")
outputs = model(**batch_dict)
attention_mask = batch_dict["attention_mask"]
hidden = outputs.last_hidden_state
reps = mean_pooling(hidden, attention_mask)
embeddings = F.normalize(reps, p=2, dim=1).detach().cpu().numpy()
return embeddings
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
queries = [INSTRUCTION + query for query in queries]
embeddings_query = encode(queries)
embeddings_doc = encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.3535913825035095, 0.18596848845481873]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]][[0.3535913825035095, 0.18596848845481873]]pythonpytorch
import torch
from sentence_transformers import SentenceTransformer
model_name = "openbmb/MiniCPM-Embedding"
model = SentenceTransformer(model_name, trust_remote_code=True, model_kwargs={ "torch_dtype": torch.float16})
# You can also use the following line to enable the Flash Attention 2 implementation
# model = SentenceTransformer(model_name, trust_remote_code=True, attn_implementation="flash_attention_2", model_kwargs={ "torch_dtype": torch.float16})
queries = ["中国的首都是哪里？"]
passages = ["beijing", "shanghai"]
INSTRUCTION = "Query: "
embeddings_query = model.encode(queries, prompt=INSTRUCTION)
embeddings_doc = model.encode(passages)
scores = (embeddings_query @ embeddings_doc.T)
print(scores.tolist()) # [[0.35365450382232666, 0.18592746555805206]]Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.