Skip to content

Add scalar LoRA value-head (critic) support for SAO-style RL - #85

Open
qywu wants to merge 8 commits into
mainfrom
qywu/value-head-critic
Open

Add scalar LoRA value-head (critic) support for SAO-style RL#85
qywu wants to merge 8 commits into
mainfrom
qywu/value-head-critic

Raise worker ack_timeout to 1800s

f9f3f2d
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar