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

[RWKV7] Fix masking before time shifting modules #141

Merged
merged 5 commits into from
Jan 24, 2025
Merged

[RWKV7] Fix masking before time shifting modules #141

merged 5 commits into from
Jan 24, 2025

Conversation

Triang-jyed-driung
Copy link
Contributor

  1. Implemented attention mask for Channel-mixing module
  2. Fixed returning None for logits
  3. Always launch chunk kernel if training

@Triang-jyed-driung
Update modeling_rwkv7.py
20f231d 
1. Fix not returning logits
2. Mask channel mix
@Triang-jyed-driung
Update rwkv7.py
f8cef29 
Always launch `chunk` kernel when training
@yzhangcs yzhangcs changed the title RWKV-7 fixes [RWKV7] Fix masking before time shifting modules Jan 24, 2025
@yzhangcs yzhangcs merged commit 0272073 into fla-org:main Jan 24, 2025
1 check failed
@yzhangcs
Copy link
Member

Cool! Thank you.

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.
2 participants
@Triang-jyed-driung @yzhangcs