PunjabiSBERT-STS

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

pip install -U sentence-transformers

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)

Sin sentence-transformers, puedes usar el modelo así: Primero, pasas tu entrada a través del modelo transformer, luego tienes que aplicar la operación de agrupamiento correcta sobre las incrustaciones de palabras contextualizadas.

from transformers import AutoTokenizer, AutoModel
import torch

#Mean Pooling - Tomar la máscara de atención en cuenta para el promediado correcto
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #El primer elemento de model_output contiene todas las incrustaciones de token
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 we want sentence embeddings for
sentences = ["This is an example sentence", "Each sentence is converted"]

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

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