模型:

sentence-transformers/msmarco-distilbert-base-v3

英文

sentence-transformers/msmarco-distilbert-base-v3

这是一个 sentence-transformers 模型:它将句子和段落映射到一个768维的稠密向量空间,可用于聚类或语义搜索等任务。

使用(Sentence-Transformers)

当你安装了 sentence-transformers 之后,使用这个模型就很简单:

pip install -U sentence-transformers

然后你可以像这样使用模型:

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

model = SentenceTransformer('sentence-transformers/msmarco-distilbert-base-v3')
embeddings = model.encode(sentences)
print(embeddings)

使用(HuggingFace Transformers)

如果没有 sentence-transformers ,你可以这样使用模型:首先,将输入通过变换器模型,然后你必须在上下文化的词嵌入之上应用正确的汇聚操作。

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/msmarco-distilbert-base-v3')
model = AutoModel.from_pretrained('sentence-transformers/msmarco-distilbert-base-v3')

# 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)

评估结果

对于此模型的自动评估,请参阅句子嵌入基准 : https://seb.sbert.net

完整的模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 510, '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})
)

引用及作者

该模型是由 sentence-transformers 进行训练的。

如果您觉得这个模型有帮助,请随意引用我们的出版物 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",
}