---
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: text-classification
---

# 🔍 BGE Reranker Base (Fine-tuned)

This repository contains a **fine-tuned cross-encoder reranker model** based on `BAAI/bge-reranker-base`.

It is designed to improve retrieval pipelines by re-ranking top-K results from embedding models.

---

## 🚀 Key Features

- Cross-encoder reranking (query + passage scoring)
- Strong performance on MTEB / C-MTEB benchmarks
- Supports multilingual (English + Chinese)
- Optimized for semantic search pipelines

---

## 📦 Model Files

This repo contains:

✔ config.json  
✔ model.safetensors  
✔ tokenizer_config.json  
✔ sentencepiece.bpe.model  
✔ special_tokens_map.json (fixed naming)  
✔ README.md  


## ⚙️ Usage

### 🔹 Using FlagEmbedding (Recommended)

```python
from FlagEmbedding import FlagReranker

reranker = FlagReranker("BAAI/bge-reranker-base", use_fp16=True)

score = reranker.compute_score(["query", "passage"])
print(score)