# 使用 Unsloth 参加 AMD AI 强化学习黑客松

您可以在此查看 Unsloth 的 GitHub 仓库： <https://github.com/unslothai/unsloth>

这是我们 AMD 微调笔记本的链接：

{% embed url="<https://github.com/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_Reinforcement_Learning_2048_Game_BF16.ipynb>" %}

<https://github.com/unslothai/notebooks/blob/main/nb/gpt_oss_(20B)_Reinforcement_Learning_2048_Game_BF16.ipynb>

{% code overflow="wrap" %}

```bash
wget 'https://raw.githubusercontent.com/unslothai/notebooks/refs/heads/main/nb/gpt_oss_(20B)_Reinforcement_Learning_2048_Game_BF16.ipynb'
```

{% endcode %}

如果想升级 Unsloth / Unsloth Zoo：

{% code overflow="wrap" %}

```bash
uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm7.0 --upgrade --force-reinstall

pip uninstall unsloth unsloth_zoo -y && \
    pip install git+https://github.com/unslothai/unsloth-zoo git+https://github.com/unslothai/unsloth --no-deps --force-reinstall --no-cache-dir
```

{% endcode %}

关于 bitsandbytes：

```bash
pip install "unsloth[amd] @ git+https://github.com/unslothai/unsloth"
```

如果您看到：

{% code overflow="wrap" %}

```
错误：安装失败：bitsandbytes-1.33.7rc0-py3-none-manylinux_2_24_x86_64.whl (bitsandbytes==1.33.7rc0 (来自 https://github.com/bitsandbytes-foundation/bitsandbytes/releases/download/continuous-release_main/bitsandbytes-1.33.7.preview-py3-none-manylinux_2_24_x86_64.whl)) 原因：Wheel 版本与文件名不匹配 (0.49.2.dev0 != 1.33.7rc0)，这表示 Wheel 格式不正确。如果这是故意的，请设置 UV_SKIP_WHEEL_FILENAME_CHECK=1。
```

{% endcode %}

不要使用 UV\_SKIP\_WHEEL\_FILENAME\_CHECK，取而代之只使用 `pip install "unsloth[amd] @ git+https://github.com/unslothai/unsloth"` （不是 uv）因为 uv 会破坏 bitsandbytes。若可能的话，也许在 PR 中添加检查来捕捉这些问题。

有关 AMD 安装说明，您可以在此查看我们的指南：

{% content-ref url="/pages/58db76de3e4da663680e51bb3a7f48ee9575ee07" %}
[AMD](/docs/zh/kai-shi-shi-yong/install/amd.md)
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/zh/kai-shi-shi-yong/install/amd/amd-hackathon.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.