transformers
more fixes for post-training llama4
#37329
Merged

more fixes for post-training llama4 #37329

winglian
github-actions github-actions marked this pull request as draft 256 days ago
github-actions
winglian winglian marked this pull request as ready for review 256 days ago
github-actions github-actions requested a review from ArthurZucker ArthurZucker 256 days ago
github-actions github-actions requested a review from Rocketknight1 Rocketknight1 256 days ago
ArthurZucker
ArthurZucker approved these changes on 2025-04-07
winglian more fixes for post-training llama4
7d56e1c4
winglian use target_length instead of guearded past_key_values
dd06245d
winglian winglian force pushed from 2881abef to dd06245d 256 days ago
ArthurZucker
ArthurZucker approved these changes on 2025-04-07
ArthurZucker
ArthurZucker ArthurZucker merged b54c2f46 into main 256 days ago
ArthurZucker ArthurZucker added for patch
ArthurZucker
ArthurZucker
vasqu

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone