bge small zh v1.5

提供商BAAI
分类feature-extraction
许可证mit
下载量2.8M
星标47

简介

bge-small-zh-v1.5 是由北京智源人工智能研究院（BAAI）推出的轻量级中文文本向量化模型。它专注于将文本转化为高质量的向量表示，是构建 RAG（检索增强生成）系统的核心组件。相比于大语言模型，它的体积极小，推理速度极快，非常适合部署在资源受限的端侧设备或作为大规模知识库的索引工具。对于开发者而言，它能显著提升语义搜索的精度，解决传统关键词匹配无法处理的语义偏差问题，上手门槛低，可无缝集成至 LangChain 或 LlamaIndex 等主流框架中。

核心亮点

  • 极致轻量，低延迟，适合高并发检索场景
  • 中文语义对齐能力强，大幅提升 RAG 检索精度
  • MIT 协议开源，企业级部署无压力
  • 完美兼容主流向量数据库与 AI 开发框架

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("BAAI/bge-small-zh-v1.5")
tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-small-zh-v1.5")

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 BAAI/bge-small-zh-v1.5

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 BAAI/bge-small-zh-v1.5 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('BAAI/bge-small-zh-v1.5')

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/BAAI/bge-small-zh-v1.5

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/BAAI/bge-small-zh-v1.5

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('BAAI/bge-small-zh-v1.5')
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-small-zh-v1.5')

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 BAAI/bge-small-zh-v1.5

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 BAAI/bge-small-zh-v1.5 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('BAAI/bge-small-zh-v1.5')

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/BAAI/bge-small-zh-v1.5.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/BAAI/bge-small-zh-v1.5.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', 'BAAI/bge-small-zh-v1.5')

完整文档

来源: HuggingFace

---
license: mit
language:

  • zh

---

<h1 align="center">FlagEmbedding</h1>

<h4 align="center">
<p>
<a href=#model-list>Model List</a> |
<a href=#frequently-asked-questions>FAQ</a> |
<a href=#usage>Usage</a> |
<a href="#evaluation">Evaluation</a> |
<a href="#train">Train</a> |
<a href="#contact">Contact</a> |
<a href="#citation">Citation</a> |
<a href="#license">License</a>
<p>
</h4>

More details please refer to our Github: FlagEmbedding.

English | 中文

FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search.
And it also can be used in vector databases for LLMs.

*********** 🌟Updates🌟 *********

  • 10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper :fire:



  • 09/12/2023: New models:

- New reranker model: release cross-encoder models BAAI/bge-reranker-base and BAAI/bge-reranker-large, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.
- update embedding model**: release bge-*-v1.5 embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.

<details>
<summary>More</summary>
<!-- ### More -->

  • 09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning.

  • 08/09/2023: BGE Models are integrated into Langchain, you can use it like this; C-MTEB leaderboard is available.

  • 08/05/2023: Release base-scale and small-scale models, best performance among the models of the same size 🤗

  • 08/02/2023: Release bge-large-*(short for BAAI General Embedding) Models, rank 1st on MTEB and C-MTEB benchmark! :tada: :tada:



</details>

Model List

bge is short for BAAI general embedding.

| Model | Language | | Description | query instruction for retrieval [1] |
|:-------------------------------|:--------:| :--------:| :--------:|:--------:|
| BAAI/llm-embedder | English | Inference Fine-tune | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See README |
| BAAI/bge-reranker-large | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | |
| BAAI/bge-reranker-base | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | |
| BAAI/bge-large-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-base-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-small-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-large-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-base-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-small-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-large-en | English | Inference Fine-tune | :trophy: rank 1st in MTEB leaderboard | Represent this sentence for searching relevant passages: |
| BAAI/bge-base-en | English | Inference Fine-tune | a base-scale model but with similar ability to bge-large-en | Represent this sentence for searching relevant passages: |
| BAAI/bge-small-en | English | Inference Fine-tune |a small-scale model but with competitive performance | Represent this sentence for searching relevant passages: |
| BAAI/bge-large-zh | Chinese | Inference Fine-tune | :trophy: rank 1st in C-MTEB benchmark | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-base-zh | Chinese | Inference Fine-tune | a base-scale model but with similar ability to bge-large-zh | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-small-zh | Chinese | Inference Fine-tune | a small-scale model but with competitive performance | 为这个句子生成表示以用于检索相关文章： |

[1\]: If you need to search the relevant passages to a query, we suggest to add the instruction to the query; in other cases, no instruction is needed, just use the original query directly. In all cases, no instruction needs to be adde

查看官方来源