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

Assumes CUDA, doesn't use safetensors #5

Open
Vargol opened this issue Mar 23, 2024 · 2 comments
Open

Assumes CUDA, doesn't use safetensors #5

Vargol opened this issue Mar 23, 2024 · 2 comments

Comments

@Vargol
Copy link

Vargol commented Mar 23, 2024

HI any chance you could change the checkpoint to be safetensor format, and maybe change the code not to assume the device is CUDA.

There are a lot of people that want to run stuff like this on MPS for example, and pickle files can contain executable code so should not be offered as a file format for security reasons.

@FreakTheMighty
Copy link

@Vargol is it possible to convert existing checkpoints or does that need to be retrained?

@Vargol
Copy link
Author

Vargol commented Apr 3, 2024

Should be able to convert, safe tensors is just a way to store tensors without the possibility of embedded code running while loading. I'm not an expert though, but no one should be using formats that can execute code just by loading the files these days.

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

No branches or pull requests

2 participants