-
Notifications
You must be signed in to change notification settings - Fork 9
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.
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
Add another LayerNorm to MLPSpeculator #35
Add another LayerNorm to MLPSpeculator #35
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A comment regarding tie_wts
. Looks like we are missing some MixtralConfig
in the test as well (could be a transformers version). You may want to update the transformers version to a higher one as I believe we should support it.
fms_extras/models/speculator.py
Outdated
@@ -50,13 +50,16 @@ def __init__( | |||
tie_emb=False, | |||
tie_head=False, | |||
tie_transition=False, | |||
tie_wts=False, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is this just a way to simplify doing tie_emb, tie_head, tie_transition = True. If so, I think it would be better to just remove this and use the tie_emb, tie_head, tie_transition more explicitly.
Closing this one-- redundant after #36 |
No description provided.