Pinned Loading
Repositories
Showing 5 of 5 repositories
-
- AutoSFT Public
AutoSFT is an AI system that post-trains AI: a multi-agent research policy that iteratively designs the SFT data recipe, with a fixed base model, trainer, and budget.
- One-Shot-OPD Public
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
- Rethinking-OPD Public
[TMLR] Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Top languages
Loading…
Most used topics
Loading…