本文档部署一次的时间为，够买机器开始时间：18:08:37 大模型下载完成结束时间：19:36

服务器买的：https://www.ucloud.cn/site/active/new/gpu.html

目前是9.9块钱24小时，注意现存务必24G

购买的时候选centos：

服务带了conda，不用安装，很方便，显卡RTX40，cuda版本12.2，目录：/usr/local/cuda-12.2/

遇到问题：

安装 pip install modelscope的时候报错：

============================ERROR=====================
CUDA SETUP: CUDA detection failed! Possible reasons:

1. You need to manually override the PyTorch CUDA version. Please see: “https://github.com/TimDettmers/bitsandbytes/blob/main/how_to_use_nonpytorch_cuda.md
2. CUDA driver not installed
3. CUDA not installed
4. You have multiple conflicting CUDA libraries
5. Required library not pre-compiled for this bitsandbytes release!
   CUDA SETUP: If you compiled from source, try again with make CUDA_VERSION=DETECTED_CUDA_VERSION for example, make CUDA_VERSION=113.

CUDA SETUP: The CUDA version for the compile might depend on your conda install. Inspect CUDA version via conda list | grep cuda.

2. 问题解决
   在环境变量LD_LIBRARY_PATH中增加CUDA的lib路径:

export PATH=/usr/local/cuda-12.2/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-12.2/lib64:$LD_LIBRARY_PATH
然后重新安装bitsandbytes即可：

pip uninstall bitsandbytes
pip install bitsandbytes
最后正常加载模型并训练：