zhyxun

> i have solved the question,thanks. How did you solve the problem? I have the same problem.

> you can follow the repo https://zhuanlan.zhihu.com/p/147144376, download the "bert-base-uncased" folder from https://huggingface.co/bert-base-uncased, and modify the error pretrain location to your local position. Thanks very much!

@github-eliviate @grimoire 这个问题解决了吗？我今天安装了最新的lmdeply==0.7.2，调用QwenVL2-5_72B，遇到了同样的问题。

@grimoire ### 环境信息 NVIDIA-SMI 535.161.08 Driver Version: 535.161.08 CUDA Version: 12.4 python版本是Python 3.10.12 Package Version ----------------------------- ------------- accelerate 0.33.0 addict 2.4.0 aiofiles 23.2.1 aiohappyeyeballs 2.4.0 aiohttp 3.10.5 aiosignal 1.3.1 airportsdata...

@grimoire 试试这样图片呢？跑大概五六分钟就会出现错误，有时候甚至更短，两三分钟就会报错  你跑着没问题吗？

> [@zhyxun](https://github.com/zhyxun) [#3307](https://github.com/InternLM/lmdeploy/pull/3307) 试试看 太感谢了，这个方法解决了我的问题。