Commit History

Autor SHA1 Mensaxe Data
  Jeff Tang 7edf3d8df0 llm as a judge running now hai 3 semanas
  Jeff Tang 57c05170eb added llm as a judge reward func hai 4 semanas
  Jeff Tang c88e10fab6 grpo llama 3.2 3b with 3 reward functions hai 4 semanas