sentence-transformers/paraphrase-MiniLM-L6-v2

这是一个 sentence-transformers 模型：它将句子和段落映射到 384 维的稠密向量空间，可用于聚类或语义搜索等任务。

使用方法 (Sentence-Transformers)

当你安装了 sentence-transformers 后，使用这个模型将变得非常简单：

pip install -U sentence-transformers

然后你可以这样使用该模型：

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

model = SentenceTransformer('sentence-transformers/paraphrase-MiniLM-L6-v2')
embeddings = model.encode(sentences)
print(embeddings)

使用方法 (HuggingFace Transformers)

如果没有使用 sentence-transformers，你可以像这样使用该模型：首先将输入通过 transformer 模型，然后需要在上下文词嵌入之上应用正确的池化操作。

from transformers import AutoTokenizer, AutoModel
import torch


# Mean Pooling - 考虑注意力掩码以正确计算平均值
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] # model_output 的第一个元素包含所有 token 嵌入
    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)


# 我们想要获取句子嵌入的句子
sentences = ['This is an example sentence', 'Each sentence is converted']

# 从 HuggingFace Hub 加载模型
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-MiniLM-L6-v2')

# 对句子进行分词
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# 计算 token 嵌入
with torch.no_grad():
    model_output = model(**encoded_input)

# 执行池化。这里使用最大池化作为示例。
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("句子嵌入：")
print(sentence_embeddings)

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

引用 & 作者

该模型由 sentence-transformers 训练。

如果你觉得这个模型有帮助，欢迎引用我们的论文 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",
}