S-Scibert-snli-multinli-stsb

Usando Sentence-Transformers

Instalar sentence-transformers:

pip install -U sentence-transformers

Luego puede usar el modelo de esta manera:

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

model = SentenceTransformer('pritamdeka/S-Scibert-snli-multinli-stsb')
embeddings = model.encode(sentences)
print(embeddings)

Usando HuggingFace Transformers

Sin sentence-transformers, puede usar el modelo de esta manera: Primero, pasa su entrada a través del modelo transformer, luego debe aplicar la operación de 'pooling' correcta sobre las incrustaciones de palabras contextualizadas.

from transformers import AutoTokenizer, AutoModel
import torch

def mean_pooling(model_output, attention_mask):
 token_embeddings = model_output[0]
 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('pritamdeka/S-Scibert-snli-multinli-stsb')
model = AutoModel.from_pretrained('pritamdeka/S-Scibert-snli-multinli-stsb')

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)