Skip to content
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

ValueError: The current device_map had weights offloaded to the disk. #3351

Open
Astrogar17 opened this issue Dec 29, 2024 · 0 comments
Open

Comments

@Astrogar17
Copy link

Hello everyone. When running the facebook_opt-66b GPT model, I encountered the following error:
ValueError: The current device_map had weights offloaded to the disk. Please provide an offload_folder for them. Alternatively, make sure you have safetensors installed if the model you are using offers the weights in this format.
Image
Image
A search of the topics on the forum did not give much result... Because in each of the topics it is suggested either to look at the answers in https://huggingface.co/blog/accelerate-large-models or to add lines of code in .py files... but the problem is that I just do not know where and what code to add... Therefore, if someone writes a step-by-step description of how to fix this problem, I will be very grateful!!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant