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.

Sign up for GitHub

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

Jump to bottom

Fix/dpo #23

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix/dpo #23

wants to merge 2 commits into from

Conversation

Erland366
Copy link

This enabling DPO training for VLM models.

uncompiled_cross_entropy_loss function actually missing labels arguments.

on DPO, I think what's happening is that the status is actually training but there's no labels. So I removed that self.training part.

@Erland366
Copy link
Author

unslothai/unsloth#1367 (comment)

related issue

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@Erland366