TA-OPD. The implementation of Teachability-Aware On-Policy Distillation (TA-OPD), the method introduced in Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation.

github.com/wyy-code/TA-OPD

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

No recent activity.