LLM-Tuning icon indicating copy to clipboard operation
LLM-Tuning copied to clipboard

baichuan-13b reward model训练

Open endlesstalking opened this issue 1 year ago • 0 comments

请问有baichuan-13b的modeling_baichuan_for_cls.py吗?

baichuan-13b和baichuan7b模型结构有些调整,直接基于7b的cls.py文件训练reward model会模型参数不一致的问题

感谢~

image

endlesstalking avatar Aug 11 '23 07:08 endlesstalking