Skip to content

Add OPSD (On-Policy Distillation) training example#1002

Merged
delock merged 25 commits into
masterfrom
gma/opsd
Jul 15, 2026
Merged

Add OPSD (On-Policy Distillation) training example#1002
delock merged 25 commits into
masterfrom
gma/opsd

Remove unused shift_for_next_token_prediction helper and its test

9eb0c4f
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Jul 13, 2026 in 1s

DCO

All commits are signed off!