模型:

sentence-transformers/distilbert-base-nli-stsb-mean-tokens

英文

⚠️ 此模型已废弃,请勿使用,因为生成的句子嵌入质量较低。您可以在此处找到推荐的句子嵌入模型: SBERT.net - Pretrained Models

sentence-transformers/distilbert-base-nli-stsb-mean-tokens

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。

用法(Sentence-Transformers)

安装了带有 sentence-transformers 的情况下,可以轻松使用该模型:

pip install -U sentence-transformers

然后,您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/distilbert-base-nli-stsb-mean-tokens')
embeddings = model.encode(sentences)
print(embeddings)

用法(HuggingFace Transformers)

没有 sentence-transformers ,您可以像这样使用模型:首先,将输入传递给变换器模型,然后必须在上下文词嵌入上应用正确的汇集操作。

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/distilbert-base-nli-stsb-mean-tokens')
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-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)

评估结果

若要对此模型进行自动评估,请参见 句子嵌入基准

: https://seb.sbert.net

完整的模型架构

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})
)

引用和作者

该模型由 sentence-transformers 训练。

如果您发现此模型有帮助,请随时引用我们的出版物 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",
}