update the pre-built version of bitsandbytes library for windows us…

…er to support QLoRA
wanli2014 · Jul 3, 2023 · d9506a9 · d9506a9
1 parent 3b0ee1e
commit d9506a9
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -105,10 +105,10 @@ cd ChatGLM-Efficient-Tuning
 pip install -r requirements.txt
 ```
 
-If you want to enable LoRA or Freeze quantization on Windows, you will be required to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.6 or 11.7.
+If you want to enable LoRA(QLoRA) or Freeze quantization on Windows, you will be required to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.1.
 
 ```
-pip install https://github.com/acpopescu/bitsandbytes/releases/download/v0.37.2-win.1/bitsandbytes-0.37.2-py3-none-any.whl
+pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.39.1-py3-none-win_amd64.whl
 ```
 
 ### Fine-tuning with a Single GPU

diff --git a/README_zh.md b/README_zh.md
@@ -111,10 +111,10 @@ cd ChatGLM-Efficient-Tuning
 pip install -r requirements.txt
 ```
 
-对于 Windows 用户，若要启用 LoRA 或 Freeze 的量化微调，请下载预构建的 `bitsandbytes` 包，目前仅支持 CUDA 11.6 和 11.7。
+对于 Windows 用户，若要启用 LoRA（QLoRA） 或 Freeze 的量化微调，请下载预构建的 `bitsandbytes` 包，目前支持 CUDA 11.1 到12.1。
 
 ```
-pip install https://github.com/acpopescu/bitsandbytes/releases/download/v0.37.2-win.1/bitsandbytes-0.37.2-py3-none-any.whl
+pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.39.1-py3-none-win_amd64.whl
 ```
 
 ### 单 GPU 微调训练