quicktensor/dexml_eurlex-4k

Uso de Inferencia (Transformadores de Oraciones)

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('quicktensor/dexml_eurlex-4k')
embeddings = model.encode(sentences)
print(embeddings)

Uso (Transformadores de HuggingFace)

from transformers import AutoTokenizer, AutoModel
import torch
import torch.nn.functional as F

pooler = lambda x: F.normalize(x[:, 0, :], dim=-1) # Choose CLS token and normalize

sentences = ["This is an example sentence", "Each sentence is converted"]
tokenizer = AutoTokenizer.from_pretrained('quicktensor/dexml_eurlex-4k')
model = AutoModel.from_pretrained('quicktensor/dexml_eurlex-4k')

encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
    embeddings = pooler(model(**encoded_input))

print(embeddings)