transformers
Fix DBRX MoE hidden size and expert GLU transposes
#47671
Merged

Fix DBRX MoE hidden size and expert GLU transposes #47671

kaixuanliu
kaixuanliu Fix DBRX MoE hidden size and expert GLU transposes
262a8bee
kaixuanliu kaixuanliu marked this pull request as ready for review 6 days ago
github-actions github-actions requested a review from ArthurZucker ArthurZucker 6 days ago
github-actions github-actions requested a review from ydshieh ydshieh 6 days ago
kaixuanliu
vasqu
vasqu approved these changes on 2026-08-03
vasqu
github-actions
HuggingFaceDocBuilderDev
github-actions
vasqu
kaixuanliu update
e6c87da1
kaixuanliu propogate self.d_model to ffn_config.hidden_size
e8a1ff9a
kaixuanliu
kaixuanliu update
116c76e0
kaixuanliu update
77dead05
github-actions
kaixuanliu update comment
bc2e0ac6
github-actions
vasqu
vasqu approved these changes on 2026-08-04
vasqu
github-actions
github-actions
vasqu vasqu enabled auto-merge 4 days ago
vasqu vasqu merged 2ce15881 into main 4 days ago
kaixuanliu kaixuanliu deleted the fix-dbrx-moe-dims branch 3 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone