transformers
Fix: Mamba2 `norm_before_gate` usage
#32686
Merged

Fix: Mamba2 `norm_before_gate` usage #32686

vasqu
vasqu
vasqu
molbap
molbap approved these changes on 2024-08-14
ArthurZucker
ArthurZucker commented on 2024-08-19
vasqu
ArthurZucker
vasqu mamba2 uses norm_before_gate=False
b72e876b
vasqu small nit
4f0ce72f
vasqu remove norm_before_gate flag and follow False path only
7d01af04
vasqu vasqu force pushed to 7d01af04 1 year ago
vasqu
ArthurZucker
ArthurZucker approved these changes on 2024-08-20
HuggingFaceDocBuilderDev
ArthurZucker ArthurZucker merged c63a3d0f into main 1 year ago
vasqu vasqu deleted the mamba2-gated-norm-fix branch 1 year ago
vasqu
ArthurZucker

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone