初始化项目,由ModelHub XC社区提供模型
Model: kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward Source: Original Platform
This commit is contained in:
Model: kikiyaa/Qwen2.5-3B-Instruct-grpo-fullfinetuning-3b-customreward Source: Original Platform