transformers
fix: Initialize ApertusMLP's xielu activation using `torch_dtype`
#42864
Merged

fix: Initialize ApertusMLP's xielu activation using `torch_dtype` #42864

wasertech
wasertech wasertech force pushed from 91f68a81 to 67306014 14 days ago
wasertech
wasertech commented on 2025-12-14
wasertech wasertech force pushed from 67306014 to 26667d38 14 days ago
wasertech wasertech force pushed from 26667d38 to 1cb8b00b 14 days ago
wasertech Fix Apertus model crash on float16 hardware
4b41cf89
wasertech wasertech force pushed from 1cb8b00b to 4b41cf89 14 days ago
Rocketknight1
github-actions
HuggingFaceDocBuilderDev
Rocketknight1
wasertech
Rocketknight1
Rocketknight1 approved these changes on 2025-12-15
wasertech refactor: Move `ACT2CLS` import to top-level in Apertus models.
a660db51
github-actions
Rocketknight1 Rocketknight1 enabled auto-merge (squash) 13 days ago
Rocketknight1
Rocketknight1 Rocketknight1 merged 06378d40 into main 13 days ago
github-actions

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone