transformers
Gemma4 resizing per layer inputs
#45324
Merged

Gemma4 resizing per layer inputs #45324

zucchini-nlp
zucchini-nlp gemma4
180a0ddd
zucchini-nlp mask out per-layer input correctly!
304acd6a
HuggingFaceDocBuilderDev
zucchini-nlp revert gemma3n and add t5gemma
31bb636c
zucchini-nlp fix repo
02e4218d
zucchini-nlp the test
bbbd4340
zucchini-nlp fix some tests
431da57f
zucchini-nlp gemma3n also has a causal model
8cc8f93c
zucchini-nlp
zucchini-nlp commented on 2026-04-09
zucchini-nlp
zucchini-nlp commented on 2026-04-09
zucchini-nlp
zucchini-nlp commented on 2026-04-09
KoichiYasuoka
KoichiYasuoka commented on 2026-04-09
zucchini-nlp fix repo
a1f1f879
zucchini-nlp zucchini-nlp requested a review from ArthurZucker ArthurZucker 72 days ago
zucchini-nlp Merge branch 'main' into gemma4-resizing
8de3b7a9
zucchini-nlp
github-actions
github-actions[bot] Apply repo consistency fixes
295d36d5
ArthurZucker
ArthurZucker approved these changes on 2026-04-13
zucchini-nlp Merge remote-tracking branch 'upstream/main' into gemma4-resizing
3024c844
zucchini-nlp update attr even if weights are tied
f7efff62
github-actions
zucchini-nlp zucchini-nlp merged b6f9463e into main 66 days ago
zucchini-nlp zucchini-nlp deleted the gemma4-resizing branch 66 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone