zhouyang.xie 3f8e53e024 换用github jwjohns/unsloth-GRPO-qwen2.5 验证GRPO训练模型 hai 8 meses
..
data_raw_old.json 7270ddb56d Initialize commit hai 9 meses
data_raw_windturbine_faultcases.txt 3f8e53e024 换用github jwjohns/unsloth-GRPO-qwen2.5 验证GRPO训练模型 hai 8 meses