🚀 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
这是一个 sentence-transformers 模型,它可以将句子和段落映射到一个 768 维的密集向量空间,可用于聚类或语义搜索等任务。
🚀 快速开始
此模型是原模型 'sentence-transformers/paraphrase-multilingual-mpnet-base-v2' 的备份,因为原模型曾暂时下线。我并非该模型的作者。
✨ 主要特性
📦 安装指南
若要使用该模型,需安装 sentence-transformers:
pip install -U sentence-transformers
💻 使用示例
基础用法
当你安装了 sentence-transformers 后,使用该模型会非常简单:
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)
高级用法
若未安装 sentence-transformers,你可以按以下方式使用该模型:首先,将输入传递给 Transformer 模型,然后对上下文词嵌入应用正确的池化操作。
from transformers import AutoTokenizer, AutoModel
import torch
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0]
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 = ['This is an example sentence', 'Each sentence is converted']
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-mpnet-base-v2')
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
with torch.no_grad():
model_output = model(**encoded_input)
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
📚 详细文档
你可以通过 Sentence Embeddings Benchmark 对该模型进行自动评估:https://seb.sbert.net
🔧 技术细节
模型的完整架构如下:
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
(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})
)
📄 许可证
该模型使用的许可证为 Apache-2.0。
📚 引用与作者
该模型由 sentence-transformers 训练。
如果你觉得该模型有帮助,请引用我们的论文 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",
}