Skip to content

[rollout, trainer, cfg] feat: privileged-context teacher scoring for OPSD#6833

Draft
HaozheZhang6 wants to merge 5 commits into
verl-project:mainfrom
HaozheZhang6:feat/opsd-privileged-context
Draft

[rollout, trainer, cfg] feat: privileged-context teacher scoring for OPSD#6833
HaozheZhang6 wants to merge 5 commits into
verl-project:mainfrom
HaozheZhang6:feat/opsd-privileged-context

[rollout] refactor(opsd): branch on self_distillation instead of a so…

d31e912
Select commit
Loading
Failed to load commit list.

Workflow runs completed with no jobs