---
title: Matroyshka-ReRanker-passage
canonical_url: "https://www.modelscope.cn/models/BAAI/Matroyshka-ReRanker-passage"
md_url: "https://www.modelscope.cn/models/BAAI/Matroyshka-ReRanker-passage.md"
repository: BAAI/Matroyshka-ReRanker-passage
last_updated: 2025-05-21
license: apache-2.0
pipeline_tag: text-classification
tasks:
  - text-classification
model_type:
  - cost_wise_mistral
architectures:
  - CostWiseMistralForCausalLM
parameters: 7.1B
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 439
stars: 0
tags:
  - transformers
  - text-embeddings-inference
---

# Matroyshka-ReRanker-passage

> Matroyshka-ReRanker-passage - BAAI 在 ModelScope 开源的模型。Matroyshka Re-Ranker

BAAI/Matroyshka-ReRanker-passage 是 ModelScope 魔搭社区上的 7.1B 参数text-classification模型，采用 apache-2.0 许可。

- **Repository**: BAAI/Matroyshka-ReRanker-passage
- **License**: apache-2.0
- **Tasks**: text-classification
- **Parameters**: 7.1B
- **Tags**: transformers, text-embeddings-inference
- **Downloads**: 439
- **Stars**: 0
- **Last updated**: 2025-05-21

Source: https://www.modelscope.cn/models/BAAI/Matroyshka-ReRanker-passage

---

# Matroyshka Re-Ranker

**More details please refer to our Github: [FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding/tree/master/research/Matroyshka_reranker).**

Matroyshka Re-Ranker ([paper](https://dl.acm.org/doi/abs/10.1145/3696410.3714620))

## Usage

```
git clone https://github.com/FlagOpen/FlagEmbedding.git
cd ./FlagEmbedding/research/Matroyshka_reranker
```

```python
from rank_model import MatroyshkaReranker

compress_ratio = 2 # config your compress ratio
compress_layers = [8, 16] # cofig your layers to compress
cutoff_layers = [20, 24] # config your layers to output

reranker = MatroyshkaReranker(
    model_name_or_path='BAAI/Matroyshka-ReRanker-passage',
    peft_path=[
        './models/Matroyshka-ReRanker-passage/compensate/layer/full'
    ]
    use_fp16=True,
    cache_dir='./model_cache',
    compress_ratio=compress_ratio,
    compress_layers=compress_layers,
    cutoff_layers=cutoff_layers
)

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)
```

## Citation

If you find this repository useful, please consider giving a star and citation

```bibtex
@inproceedings{liu2025fitting,
  title={Fitting Into Any Shape: A Flexible LLM-Based Re-Ranker With Configurable Depth and Width},
  author={Liu, Zheng and Li, Chaofan and Xiao, Shitao and Li, Chaozhuo and Zhang, Chen Jason and Liao, Hao and Lian, Defu and Shao, Yingxia},
  booktitle={Proceedings of the ACM on Web Conference 2025},
  pages={3942--3951},
  year={2025}
}
```