sergeyzh/rubert-tiny-sts

Uso con la biblioteca transformers:

# pip install transformers sentencepiece
import torch
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("sergeyzh/rubert-tiny-sts")
model = AutoModel.from_pretrained("sergeyzh/rubert-tiny-sts")
# model.cuda()  # descomenta esto si tienes una GPU

def embed_bert_cls(text, model, tokenizer):
    t = tokenizer(text, padding=True, truncation=True, return_tensors='pt')
    with torch.no_grad():
        model_output = model(**{k: v.to(model.device) for k, v in t.items()})
        embeddings = model_output.last_hidden_state[:, 0, :]
        embeddings = torch.nn.functional.normalize(embeddings)
    return embeddings[0].cpu().numpy()

print(embed_bert_cls('привет мир', model, tokenizer).shape)
# (312,)

Uso con sentence_transformers:

from sentence_transformers import SentenceTransformer, util

model = SentenceTransformer('sergeyzh/rubert-tiny-sts')

oraciones = ["привет мир", "hello world", "здравствуй вселенная"]
embeddings = model.encode(oraciones)
print(util.dot_score(embeddings, embeddings))