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

bug in stablelm implementation #125

Closed
mgrabban opened this issue May 2, 2023 · 2 comments
Closed

bug in stablelm implementation #125

mgrabban opened this issue May 2, 2023 · 2 comments

Comments

@mgrabban
Copy link

mgrabban commented May 2, 2023

Hello,

Do you need the the extra layernorm here?

This is probably the bug mentioned in stablelm readme

Thanks.
@mgrabban
Copy link
Author

mgrabban commented May 2, 2023

Hello,

Do you need the the extra layernorm here?

This is probably the bug mentioned in stablelm readme

Thanks.

Nevermind, huggingface implementation also uses separate layernorms for attention and FF. So this is not the bug.

@mgrabban mgrabban closed this as completed May 2, 2023
@ggerganov
Copy link
Owner

No longer sure that I have a bug.
See my comment here: ggerganov/llama.cpp#1063 (comment)

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

No branches or pull requests
2 participants
@ggerganov @mgrabban