Skip to content

Conversation

@n28div
Copy link

@n28div n28div commented Jan 15, 2026

Fixes issue #4 by adding an additional weigths_only parameter to fix the issue:

model = xCoRe(hf_path, device, weights_only=False)

now works on my machine. The parameter defaults to True to be consistent with torch's new API, but maybe a mention in the README would be a good thing to have?

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

Successfully merging this pull request may close these issues.

1 participant