paraphrase mpnet base v2

提供商sentence-transformers
分类sentence-similarity
许可证apache-2.0
下载量2.6K
星标0

简介

paraphrase-mpnet-base-v2 是一款专注于文本语义表示的轻量级预训练模型。与传统的关键词匹配不同，它能将句子转化为高质量的向量（Embedding），精准捕捉语义相似度。对于开发者而言，它非常适合用于构建语义搜索、FAQ 自动匹配或文档去重系统。该模型在保持较低推理延迟的同时，语义理解能力显著优于早期的 BERT 系列，上手极其简单，可直接集成在 sentence-transformers 框架中，是构建 RAG（检索增强生成）应用中向量检索环节的理想选择。

核心亮点

  • 语义匹配精准，远超传统的关键词检索
  • 推理速度快，适合部署在端侧或实时服务
  • RAG 架构中理想的 Embedding 向量化工具
  • 开源协议友好，支持快速商业化集成

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("sentence-transformers/paraphrase-mpnet-base-v2")
tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/paraphrase-mpnet-base-v2")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download sentence-transformers/paraphrase-mpnet-base-v2

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download sentence-transformers/paraphrase-mpnet-base-v2 config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('sentence-transformers/paraphrase-mpnet-base-v2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('sentence-transformers/paraphrase-mpnet-base-v2')
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-mpnet-base-v2')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model sentence-transformers/paraphrase-mpnet-base-v2

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model sentence-transformers/paraphrase-mpnet-base-v2 README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('sentence-transformers/paraphrase-mpnet-base-v2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/sentence-transformers/paraphrase-mpnet-base-v2.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/sentence-transformers/paraphrase-mpnet-base-v2.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'sentence-transformers/paraphrase-mpnet-base-v2')

完整文档

来源: HuggingFace

---
license: apache-2.0
library_name: sentence-transformers
tags:

  • sentence-transformers

  • feature-extraction

  • sentence-similarity

  • transformers

  • text-embeddings-inference

pipeline_tag: sentence-similarity
---

sentence-transformers/paraphrase-mpnet-base-v2

This is a sentence-transformers model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

code
pip install -U sentence-transformers

Then you can use the model like this:

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

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

Usage (HuggingFace Transformers)

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
python
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/paraphrase-mpnet-base-v2')
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-mpnet-base-v2')

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, mean pooling.

sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Usage (Text Embeddings Inference (TEI))

Text Embeddings Inference (TEI) is a blazing fast inference solution for text embedding models.

  • CPU:
bash
docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-latest \
  --model-id sentence-transformers/paraphrase-mpnet-base-v2 \
  --pooling mean \
  --dtype float16
  • NVIDIA GPU:
bash
docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cuda-latest \
  --model-id sentence-transformers/paraphrase-mpnet-base-v2 \
  --pooling mean \
  --dtype float16

Send a request to /v1/embeddings to generate embeddings via the OpenAI Embeddings API:

bash
curl -s http://localhost:8080/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sentence-transformers/paraphrase-mpnet-base-v2",
    "input": "This is an example sentence"
  }'

Or check the Text Embeddings Inference API specification instead.

Full Model Architecture

code
SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
)

Citing & Authors

This model was trained by sentence-transformers.

If you find this model helpful, feel free to cite our publication Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks:
``bibtex
@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",
}
``

查看官方来源