shibing624/text2vec-bge-large-chinese

# Usando text2vec
pip install -U text2vec

from text2vec import SentenceModel
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']

model = SentenceModel('shibing624/text2vec-bge-large-chinese')
embeddings = model.encode(sentences)
print(embeddings)

# Usando HuggingFace Transformers
pip install transformers

from transformers import BertTokenizer, BertModel
import torch

# Mean Pooling - Considerar la máscara de atención para un promedio correcto
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] # El primer elemento de la salida del modelo contiene todas las incrustaciones de tokens
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

# Cargar modelo desde HuggingFace Hub
tokenizer = BertTokenizer.from_pretrained('shibing624/text2vec-bge-large-chinese')
model = BertModel.from_pretrained('shibing624/text2vec-bge-large-chinese')
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
# Tokenizar oraciones
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Calcular incrustaciones de tokens
with torch.no_grad():
    model_output = model(**encoded_input)
    # Realizar pooling. En este caso, mean pooling.
    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print('Incrustaciones de oraciones:')
print(sentence_embeddings)

# Usando sentence-transformers
pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer

m = SentenceTransformer('shibing624/text2vec-bge-large-chinese')
sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']

sentence_embeddings = m.encode(sentences)
print('Incrustaciones de oraciones:')
print(sentence_embeddings)