---
title: RL-RAG-TOP_M-infer
canonical_url: "https://www.modelscope.cn/models/TaitaiPhu/RL-RAG-TOP_M-infer"
md_url: "https://www.modelscope.cn/models/TaitaiPhu/RL-RAG-TOP_M-infer.md"
repository: TaitaiPhu/RL-RAG-TOP_M-infer
chinese_name: "RAG系统top_m推理"
last_updated: 2026-03-02
license: "Apache License 2.0"
library_name:
  - other
frameworks:
  - other
language:
  - zh
domain:
  - RL
  - "Contextual Bandit"
downloads: 0
stars: 0
tags:
  - RL-tuned
  - ppo
---

# RL-RAG-TOP_M-infer

> RL-RAG-TOP_M-infer - TaitaiPhu 在 ModelScope 开源的模型。Use Reinforcement Learning(PPO) to train a model deciding the number of passages to include in the prompt.

TaitaiPhu/RL-RAG-TOP_M-infer 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可。

- **Repository**: TaitaiPhu/RL-RAG-TOP_M-infer
- **License**: Apache License 2.0
- **Tags**: RL-tuned, ppo
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-03-02

Source: https://www.modelscope.cn/models/TaitaiPhu/RL-RAG-TOP_M-infer

---

Use **Reinforcement Learning** to train a model deciding the number of passages to include in the prompt.

#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型


SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('TaitaiPhu/RL-RAG-TOP_M-infer')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/TaitaiPhu/RL-RAG-TOP_M-infer.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>