sentence-transformers/bert-large-nli-mean-tokens

# Uso con Sentence-Transformers
pip install -U sentence-transformers
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/bert-large-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)

# Uso con HuggingFace Transformers
from transformers import AutoTokenizer, AutoModel
import torch

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0]  # La primera parte del output del modelo contiene todos los embeddings 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)

sentences = ['This is an example sentence', 'Each sentence is converted']
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/bert-large-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/bert-large-nli-mean-tokens')
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
    model_output = model(**encoded_input)
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)