stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0

Usar este modelo es fácil cuando tienes sentence-transformers instalado:

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer
sentences = ["Isto é um exemplo", "Isto é um outro exemplo"]

model = SentenceTransformer('stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0')
embeddings = model.encode(sentences)
print(embeddings)

from transformers import AutoTokenizer, AutoModel
import torch

#Mean Pooling - Tener en cuenta la máscara de atención para una promediación correcta
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 = ['This is an example sentence', 'Each sentence is converted']

# Cargar el modelo desde HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0')
model = AutoModel.from_pretrained('stjiris/bert-large-portuguese-cased-legal-mlm-sts-v1.0')

# 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("Sentence embeddings:")
print(sentence_embeddings)