Making large AI models cheaper, faster and more accessible
[feat] Support boxed math reward (#6284)
* fix pp+tp, fix dataloader * fixed plugin micro-batch size * support boxed reward * add boxed reward * fix pp state dict incomplete issue * Revert "fix pp state dict incomplete issue" This reverts commit 6c1b3b694f4898c04575c891d5ccc205a82a3c40.
Y
YeAnbang committed
e181318d51c0fcad720b262b2765129391bb6465
Parent: fb4e507
Committed by YeAnbang <anbangy2@outlook.com>
on 8/5/2025, 5:59:02 AM