-
Notifications
You must be signed in to change notification settings - Fork 432
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
申请入群,运行infer文件报错,想请教一下如何解决! #36
Comments
看起来是cuda path的问题,可以尝试排查一下运行infer.py的环境中cuda路径是否有异常 |
我也遇到了相同的问题,老哥解决了么? |
问题解决了,你把bitsandbytes那个package uninstall一下就可以了 |
可以跑了~ |
是这样的,uninstall之后,可以跑infer.py但是训练的时候,load_in_8bit = False。这样的话,我的4090显存就会溢出了。我昨天po了问题,作者也没有解答 #48 |
作者可以成功部署了么? |
我的错误提示和你不一样,但是问题差不多,就是超不到cuda安装路径吧,提示里说了,你要sudo find / -name libcudart.so找到你的cuda所在目录,然后export LD_LIBRARY_PATH=cuda所在目录,这行加到你的~/.bashrc里 |
大概率就是这个问题,github上也有更新,针对可能的版本问题做了优化,大家可以尝试一下 |
在data/llama_data.json更换了自己的数据后,运行bash ./scripts/finetune.sh然后直接bash ./scripts/infer.sh推理时,是不是使用自己的数据微调后的模型吗? |
fine-tune后进行infer时,需要修改lora的路径再进行infer |
哥 怎么修改啊?能不能加个微信啊chen2319529093,求求你了哥 |
当我运行infer.py文件时,报错CUDA Setup failed despite GPU being available.但是,torch.cuda.is_available=true,试了很多方法都没能解决这个问题。
When I ran the infer.py file, I reported an error CUDA Setup failed despite GPU being available. However, torch. cuda. is_ Available=true, I have tried many methods but have not been able to solve this problem.
如有小伙伴知晓如何解决,请加我wechat:15665877987,不胜感激!
The text was updated successfully, but these errors were encountered: