spladev2-camembert-base-mmarcoFR

Para comenzar a utilizar el modelo, instale primero la librería:

pip install -U transformers

Luego, puede usar el modelo de la siguiente manera:

import torch
from torch.nn.functional import relu, normalize
from transformers import AutoTokenizer, AutoModel

queries = ["Ceci est un exemple de requête.", "Voici un second exemple."]
passages = ["Ceci est un exemple de passage.", "Et voilà un deuxième exemple."]

tokenizer = AutoTokenizer.from_pretrained('antoinelouis/spladev2-camembert-base-mmarcoFR')
model = AutoModel.from_pretrained('antoinelouis/spladev2-camembert-base-mmarcoFR')

q_input = tokenizer(queries, padding=True, truncation=True, return_tensors='pt')
p_input = tokenizer(passages, padding=True, truncation=True, return_tensors='pt')

with torch.no_grad():
  q_output = model(**q_input)
  p_output = model(**p_input)

q_activations = torch.amax(torch.log1p(relu(q_output.logits * q_input['attention_mask'].unsqueeze(-1))), dim=1)
p_activations = torch.amax(torch.log1p(relu(p_output.logits * p_input['attention_mask'].unsqueeze(-1))), dim=1)

q_activations = normalize(q_activations, p=2, dim=1)
p_activations = normalize(p_activations, p=2, dim=1)

similarity = q_activations @ p_activations.T
print(similarity)