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

Della tensor shape issue #528

Closed
Mandalore07 opened this issue Mar 8, 2025 · 1 comment · Fixed by #531
Closed

Della tensor shape issue #528

Mandalore07 opened this issue Mar 8, 2025 · 1 comment · Fixed by #531

Comments

@Mandalore07
Copy link

Whenever I do a della merge I get this issue:
ValueError: Trying to set a tensor of shape torch.Size([1, 8192]) in "weight" (which has shape torch. Size ( [8192])), this looks incorrect.

This issue is exclusively on della, the other merge methods work fine.
@cg123 cg123 mentioned this issue Mar 12, 2025
Merged
@cg123 cg123 closed this as completed in 5dc8023 Mar 12, 2025
@cg123
Copy link
Collaborator

cg123 commented Mar 12, 2025

Thanks for the report! This should be fixed now.

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

Successfully merging a pull request may close this issue.

Fix tensor shape change in della pruning arcee-ai/mergekit
2 participants
@cg123 @Mandalore07