sentence-transformers/paraphrase-MiniLM-L6-v2

这是一个 sentence-transformers 模型：它能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）

当您安装了 sentence-transformers 后，使用此模型会变得非常简单：

pip install -U sentence-transformers

然后你可以像这样使用该模型：

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）

如果不使用sentence-transformers，您可以这样使用该模型：首先，将输入传递给transformer模型，然后必须在上下文单词嵌入之上应用正确的池化操作。

from openmind import AutoTokenizer, AutoModel, is_torch_npu_available
from openmind_hub import snapshot_download
import torch.nn.functional as F
import torch
import argparse

def parse_args():
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to model",
        default="zhouhui/paraphrase-MiniLM-L6-v2",
    )
    args = parser.parse_args()
    return args

#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)

def main():
    args = parse_args()
    model_path = args.model_name_or_path

    if is_torch_npu_available():
        device = "npu:0"
    else:
        device = "cpu"
        
    # Sentences we want sentence embeddings for
    sentences = ['This is an example sentence', 'Each sentence is converted']

    tokenizer = AutoTokenizer.from_pretrained(model_path)
    model = AutoModel.from_pretrained(model_path)

    # 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)
    
if __name__ == "__main__":
    main()

评估结果

如需对本模型进行自动化评估，请参见 句子嵌入基准测试：https://seb.sbert.net

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})
)

引用与作者

本模型由 sentence-transformers 训练。

如果您觉得本模型有帮助，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",
}