Jeff Tang 7edf3d8df0 llm as a judge running now 4 周之前
..
deepspeed_zero3.yaml c88e10fab6 grpo llama 3.2 3b with 3 reward functions 1 月之前
grpo-llama323b-text2sql.yaml 7edf3d8df0 llm as a judge running now 4 周之前
grpo_text2sql.py 7edf3d8df0 llm as a judge running now 4 周之前
requirements.txt 57c05170eb added llm as a judge reward func 4 周之前