On-policy Distillation (Qwen3-style) #1254
euronymous-aithal
announced in
Announcements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Student generates on-policy sequences and aligns logits to a larger teacher via KL, achieving near-larger-model quality at lower cost than RL. See On-policy Distillation.
Beta Was this translation helpful? Give feedback.
All reactions