gte-large-zh

Name: gte-large-zh
Author: thenlper

59.3K

119

512

Small context

324M

1 language

license:mit

thenlper

Embedding Model

OTHER

Fair

59K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

1GB+ RAM

Mobile

Laptop

Server

Quick Summary

--- tags: - mteb - sentence-similarity - sentence-transformers - Sentence Transformers model-index: - name: gte-large-zh results: - task: type: STS dataset: type: C-MTEB/AFQMC name: MTEB AFQMC conf.

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

1GB+ RAM

Code Examples

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Usagepythontransformers

import torch.nn.functional as F
from torch import Tensor
from transformers import AutoTokenizer, AutoModel

input_texts = [
    "中国的首都是哪里",
    "你喜欢去哪里旅游",
    "北京",
    "今天中午吃什么"
]

tokenizer = AutoTokenizer.from_pretrained("thenlper/gte-large-zh")
model = AutoModel.from_pretrained("thenlper/gte-large-zh")

# Tokenize the input texts
batch_dict = tokenizer(input_texts, max_length=512, padding=True, truncation=True, return_tensors='pt')

outputs = model(**batch_dict)
embeddings = outputs.last_hidden_state[:, 0]
 
# (Optionally) normalize embeddings
embeddings = F.normalize(embeddings, p=2, dim=1)
scores = (embeddings[:1] @ embeddings[1:].T) * 100
print(scores.tolist())

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.