Simcse Roberta Large Zh

Name: Simcse Roberta Large Zh
Author: hellonlp

1 language

license:mit

hellonlp

Embedding Model

OTHER

New

21 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

Data List The following datasets are all in Chinese.

Code Examples

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

Usespythontransformers

import torch
from transformers import BertTokenizer
from transformers import BertModel
from sklearn.metrics.pairwise import cosine_similarity

# model
simcse_sup_path = "hellonlp/simcse-roberta-large-zh"
tokenizer = BertTokenizer.from_pretrained(simcse_sup_path)
MODEL = BertModel.from_pretrained(simcse_sup_path)

def get_vector_simcse(sentence):
    """
    预测simcse的语义向量。
    """
    input_ids = torch.tensor(tokenizer.encode(sentence)).unsqueeze(0)
    output = MODEL(input_ids)
    return output.last_hidden_state[:, 0].squeeze(0)

embeddings = get_vector_simcse("武汉是一个美丽的城市。")
print(embeddings.shape)
#torch.Size([1024])

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.