Commit History

Автор SHA1 Съобщение Дата
  Jeff Tang 7edf3d8df0 llm as a judge running now преди 3 седмици
  Jeff Tang 57c05170eb added llm as a judge reward func преди 4 седмици
  Jeff Tang c88e10fab6 grpo llama 3.2 3b with 3 reward functions преди 4 седмици