Name: bge reranker v2 m3
Author: BAAI

Overview

The BGE Reranker v2 M3 is a cross-encoder model designed to refine the output of initial retrieval stages in RAG pipelines. Unlike bi-encoders that rely on vector similarity, this model analyzes the specific interaction between a query and a document to provide a more precise relevancy score. It is particularly valuable for developers building multi-lingual applications, as it maintains high performance across diverse languages and handles varying document lengths effectively. By integrating this as a second-stage reranker, you can significantly reduce false positives and improve the precision of the context provided to your LLM, effectively bridging the gap between coarse retrieval and final generation.

Highlights

Optimizes RAG precision via high-accuracy cross-encoding
Strong native support for multi-lingual document retrieval
Apache-2.0 license for flexible commercial integration
Reduces LLM hallucinations by filtering irrelevant context

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("BAAI/bge-reranker-v2-m3")
tokenizer = AutoTokenizer.from_pretrained("BAAI/bge-reranker-v2-m3")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download BAAI/bge-reranker-v2-m3

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download BAAI/bge-reranker-v2-m3 config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('BAAI/bge-reranker-v2-m3')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/BAAI/bge-reranker-v2-m3

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/BAAI/bge-reranker-v2-m3

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('BAAI/bge-reranker-v2-m3')
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-m3')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model BAAI/bge-reranker-v2-m3

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model BAAI/bge-reranker-v2-m3 README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('BAAI/bge-reranker-v2-m3')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/BAAI/bge-reranker-v2-m3.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/BAAI/bge-reranker-v2-m3.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 Quickstart

Install the ModelScope library

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

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'BAAI/bge-reranker-v2-m3')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
pipeline_tag: text-classification
tags:

transformers

sentence-transformers

text-embeddings-inference

language:

multilingual

---

Reranker

More details please refer to our Github: FlagEmbedding.

Model List

Usage

Fine-tuning

Evaluation

Citation

Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding.
You can get a relevance score by inputting query and passage to the reranker.
And the score can be mapped to a float value in [0,1] by sigmoid function.

Model List

| Model | Base model | Language | layerwise | feature |
|:--------------------------------------------------------------------------|:--------:|:-----------------------------------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------:|
| BAAI/bge-reranker-base | xlm-roberta-base | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
| BAAI/bge-reranker-large | xlm-roberta-large | Chinese and English | - | Lightweight reranker model, easy to deploy, with fast inference. |
| BAAI/bge-reranker-v2-m3 | bge-m3 | Multilingual | - | Lightweight reranker model, possesses strong multilingual capabilities, easy to deploy, with fast inference. |
| BAAI/bge-reranker-v2-gemma | gemma-2b | Multilingual | - | Suitable for multilingual contexts, performs well in both English proficiency and multilingual capabilities. |
| BAAI/bge-reranker-v2-minicpm-layerwise | MiniCPM-2B-dpo-bf16 | Multilingual | 8-40 | Suitable for multilingual contexts, performs well in both English and Chinese proficiency, allows freedom to select layers for output, facilitating accelerated inference. |

You can select the model according your senario and resource.

For multilingual, utilize BAAI/bge-reranker-v2-m3 and BAAI/bge-reranker-v2-gemma

For Chinese or English, utilize BAAI/bge-reranker-v2-m3 and BAAI/bge-reranker-v2-minicpm-layerwise.

For efficiency, utilize BAAI/bge-reranker-v2-m3 and the low layer of BAAI/bge-reranker-v2-minicpm-layerwise.

For better performance, recommand BAAI/bge-reranker-v2-minicpm-layerwise and BAAI/bge-reranker-v2-gemma

Usage

Using FlagEmbedding

code

pip install -U FlagEmbedding

#### For normal reranker (bge-reranker-base / bge-reranker-large / bge-reranker-v2-m3 )

Get relevance scores (higher scores indicate more relevance):

python

from FlagEmbedding import FlagReranker
reranker = FlagReranker('BAAI/bge-reranker-v2-m3', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score) # -5.65234375
You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
score = reranker.compute_score(['query', 'passage'], normalize=True)
print(score) # 0.003497010252573502
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores) # [-8.1875, 5.26171875]
You can map the scores into 0-1 by set "normalize=True", which will apply sigmoid function to the score
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']], normalize=True)
print(scores) # [0.00027803096387751553, 0.9948403768236574]

#### For LLM-based reranker

python

from FlagEmbedding import FlagLLMReranker
reranker = FlagLLMReranker('BAAI/bge-reranker-v2-gemma', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
reranker = FlagLLMReranker('BAAI/bge-reranker-v2-gemma', use_bf16=True) # You can also set use_bf16=True to speed up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'])
print(score)
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
print(scores)

#### For LLM-based layerwise reranker

python

from FlagEmbedding import LayerWiseFlagLLMReranker
reranker = LayerWiseFlagLLMReranker('BAAI/bge-reranker-v2-minicpm-layerwise', use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
reranker = LayerWiseFlagLLMReranker('BAAI/bge-reranker-v2-minicpm-layerwise', use_bf16=True) # You can also set use_bf16=True to speed up computation with a slight performance degradation
score = reranker.compute_score(['query', 'passage'], cutoff_layers=[28]) # Adjusting 'cutoff_layers' to pick which layers are used for computing the score.
print(score)
scores = reranker.compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']], cutoff_layers=[28])
print(scores)

Using Huggingface transformers

#### For normal reranker (bge-reranker-base / bge-reranker-large / bge-reranker-v2-m3 )

Get relevance scores (higher scores indicate more relevance):

python

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-reranker-v2-m3')
model = AutoModelForSequenceClassification.from_pretrained('BAAI/bge-reranker-v2-m3')
model.eval()
pairs = [['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']]
with torch.no_grad():
    inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
    scores = model(**inputs, return_dict=True).logits.view(-1, ).float()
    print(scores)

#### For LLM-based reranker

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

def get_inputs(pairs, tokenizer, prompt=None, max_length=1024):
if prompt is None:
prompt = "Given a query A and a passage B, determine whether the passage contains an answer to the query by providing a prediction of either 'Yes' or 'No'."
sep = "\n"
prompt_inputs = tokenizer(prompt,