par sentence-transformers
Open source · 309k downloads · 13 likes
Ce modèle, bien que désormais obsolète, était conçu pour transformer des phrases ou des paragraphes en vecteurs denses de 768 dimensions, facilitant ainsi des tâches comme le regroupement de données ou la recherche sémantique. Il appartenait à la famille des modèles *sentence-transformers*, optimisés pour capturer le sens global des textes plutôt que des mots isolés. Ses principales capacités résidaient dans la génération d'embeddings utilisables pour comparer des similarités entre phrases ou documents de manière efficace. Il se distinguait par sa légèreté et sa rapidité, héritant des avantages de l'architecture DistilBERT tout en étant spécialement entraîné pour des tâches de traitement du langage naturel. Malgré ses limites en qualité d'embeddings, il a marqué une étape importante dans l'évolution des modèles de représentation textuelle.
⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: SBERT.net - Pretrained Models
This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/distilbert-base-nli-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)
Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
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('sentence-transformers/distilbert-base-nli-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-mean-tokens')
# 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, max pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
This model was trained by sentence-transformers.
If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}