XuanRen4470
Results
3
comments of
XuanRen4470
> DPO 不是用来刷数据集准确率的 但是我记得dpo是可以拿来提高模型能力的呀？还有dpo具体的流程究竟是什么呀？我现在加了一个merge sft lora的操作好像准确率有提高。可是readme的dpo example里没有提到merge lora。我现在inference和train的流程和readme里全都不一样但是准确率好像高了一些。
same error, any solution?
same for me. i am also working on multi turn rl . my wechat is x34ren. could you please add me to the group?