bge reranker large

提供商BAAI
分类feature-extraction
许可证mit
下载量371.6K
星标68

简介

bge-reranker-large 是由北京智源人工智能研究院（BAAI）开发的深度重排序模型。在 RAG（检索增强生成）流程中，它通常接在向量检索之后，对初筛出的候选文档进行二次精排，以解决向量检索在语义匹配上可能存在的“偏差”问题。该模型能够更精准地计算查询词与文档的相关性，显著提升最终交给 LLM 的上下文质量。对于开发者而言，它部署简单，是优化知识库问答准确率、降低模型幻觉的性价比极高之选。

核心亮点

  • 大幅提升 RAG 检索精度，减少无关文档干扰
  • 弥补向量检索短板，实现语义级精准重排
  • MIT 协议开源，支持私有化部署且无商用压力
  • 适配多种中文知识库场景，上手门槛极低

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-reranker-large")
tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-reranker-large")

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-reranker-large

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-reranker-large 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-reranker-large')

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-reranker-large

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-reranker-large

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-reranker-large')
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-large')

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-reranker-large

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-reranker-large 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-reranker-large')

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-reranker-large.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-reranker-large.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-reranker-large')

完整文档

来源: HuggingFace

---
license: mit
language:

  • en

  • zh

tags:
  • mteb

model-index:
  • name: bge-reranker-base

results:
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv1-reranking
name: MTEB CMedQAv1
config: default
split: test
revision: None
metrics:
- type: map
value: 81.27206722525007
- type: mrr
value: 84.14238095238095
- task:
type: Reranking
dataset:
type: C-MTEB/CMedQAv2-reranking
name: MTEB CMedQAv2
config: default
split: test
revision: None
metrics:
- type: map
value: 84.10369934291236
- type: mrr
value: 86.79376984126984
- task:
type: Reranking
dataset:
type: C-MTEB/Mmarco-reranking
name: MTEB MMarcoReranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 35.4600511272538
- type: mrr
value: 34.60238095238095
- task:
type: Reranking
dataset:
type: C-MTEB/T2Reranking
name: MTEB T2Reranking
config: default
split: dev
revision: None
metrics:
- type: map
value: 67.27728847727172
- type: mrr
value: 77.1315192743764
pipeline_tag: feature-extraction
---

We have updated the new reranker, supporting larger lengths, more languages, and achieving better performance.

<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="#citation">Citation</a> |
<a href="#license">License</a>
<p>
</h4>

More details please refer to our Github: FlagEmbedding.

English | 中文

FlagEmbedding focuses on retrieval-augmented LLMs, consisting of the following projects currently:

News

  • 3/18/2024: Release new rerankers, built upon powerful M3 and LLM (GEMMA and MiniCPM, not so large actually) backbones, supporitng multi-lingual processing and larger inputs, massive improvements of ranking performances on BEIR, C-MTEB/Retrieval, MIRACL, LlamaIndex Evaluation.
  • 3/18/2024: Release Visualized-BGE, equipping BGE with visual capabilities. Visualized-BGE can be utilized to generate embeddings for hybrid image-text data.
  • 1/30/2024: Release BGE-M3, a new member to BGE model series! M3 stands for Multi-linguality (100+ languages), Multi-granularities (input length up to 8192), Multi-Functionality (unification of dense, lexical, multi-vec/colbert retrieval).
It is the first embedding model which supports all three retrieval methods, achieving new SOTA on multi-lingual (MIRACL) and cross-lingual (MKQA) benchmarks. Technical Report and Code. :fire:
  • 1/9/2024: Release Activation-Beacon, an effective, efficient, compatible, and low-cost (training) method to extend the context length of LLM. Technical Report :fire:
  • 12/24/2023: Release LLaRA, a LLaMA-7B based dense retriever, leading to state-of-the-art performances on MS MARCO and BEIR. Model and code will be open-sourced. Please stay tuned. Technical Report
  • 11/23/2023: Release LM-Cocktail, a method to maintain general capabilities during fine-tuning by merging multiple language models. Technical Report :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/bge-m3 | Multilingual | Inference Fine-tune | Multi-Functionality(dense retrieval, sparse retrieval, multi-vector(colbert)), Multi-Linguality, and Multi-Granularity(8192 tokens) | |
| 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](https://hugging

查看官方来源