biencoder-electra-base-mmarcoFR

Usando Sentence-Transformers

from sentence_transformers import SentenceTransformer

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

model = SentenceTransformer('antoinelouis/biencoder-electra-base-french-mmarcoFR')
q_embeddings = model.encode(queries, normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)

similarity = q_embeddings @ p_embeddings.T
print(similarity)

Usando FlagEmbedding

from FlagEmbedding import FlagModel

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

model = FlagModel('antoinelouis/biencoder-electra-base-french-mmarcoFR')
q_embeddings = model.encode(queries, normalize_embeddings=True)
p_embeddings = model.encode(passages, normalize_embeddings=True)

similarity = q_embeddings @ p_embeddings.T
print(similarity)

Usando Transformers

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

def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] # Primer elemento de model_output contiene todas las codificaciones 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)

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/biencoder-electra-base-french-mmarcoFR')
model = AutoModel.from_pretrained('antoinelouis/biencoder-electra-base-french-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_embeddings = mean_pooling(q_output, q_input['attention_mask'])
    q_embeddings = normalize(q_embeddings, p=2, dim=1)
    p_embeddings = mean_pooling(p_output, p_input['attention_mask'])
    p_embeddings = normalize(p_embeddings, p=2, dim=1)

similarity = q_embeddings @ p_embeddings.T
print(similarity)