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 T5Encoder model handling. #12590

Merged
merged 1 commit into from
Mar 27, 2025
Merged

Fix T5Encoder model handling. #12590

merged 1 commit into from
Mar 27, 2025

Conversation

HighDoping
Copy link
Contributor

Fix T5Encoder model handling. Fix issues HighDoping/Wan2.1#2 and #12588.

@fairydreaming fairydreaming linked an issue Mar 27, 2025 that may be closed by this pull request
Eval bug: T5Encoder support broken #12588
Closed
fairydreaming
fairydreaming approved these changes Mar 27, 2025
View reviewed changes
Copy link
Collaborator

@fairydreaming fairydreaming left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I confirm that it restores the correct operation of T5Encoder models. Tested with llama-embedding tool and stable diffusion 3 text encoder model - with this patch the calculated embeddings are the same as in my original implementation.

@fairydreaming
Copy link
Collaborator

@ggerganov Is there any specific reason for commenting out T5Encoder support?

@ggerganov
Copy link
Member

No, I think I have forgot to re-enable it. Good to merge.

@fairydreaming fairydreaming merged commit 953c2a6 into ggml-org:master Mar 27, 2025
48 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fairydreaming fairydreaming

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

Eval bug: T5Encoder support broken
3 participants
@HighDoping @fairydreaming @ggerganov