turkish-base-bert-uncased-mean-nli-stsb-tr

Uso (Sentence-Transformers)

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer
sentences = ["Bu örnek bir cümle", "Her cümle dönüştürülür"]

model = SentenceTransformer('atasoglu/turkish-base-bert-uncased-mean-nli-stsb-tr')
embeddings = model.encode(sentences)
print(embeddings)

Uso (HuggingFace Transformers)

from transformers import AutoTokenizer, AutoModel
import torch

#Mean Pooling - Tome en cuenta la máscara de atención para un promedio correcto
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #El primer elemento de model_output 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)

# Oraciones para las que queremos incrustaciones de oraciones
sentences = ["Bu örnek bir cümle", "Her cümle dönüştürülür"]

# Cargar modelo desde HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('atasoglu/turkish-base-bert-uncased-mean-nli-stsb-tr')
model = AutoModel.from_pretrained('atasoglu/turkish-base-bert-uncased-mean-nli-stsb-tr')

# 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 el pooling. En este caso, pooling promedio.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Incrustaciones de oraciones:")
print(sentence_embeddings)