Closed ZhihaoAIRobotic closed 5 months ago
There is a bug when SFT InternLM-XComposer2 with gradient checkpointing, which seems a bug from the upstream dependency trl/sft_trainer
. I recommend to use the official sft script of this model for best practice currently.
Does this repo support for SFT InternLM-XComposer2 ?
There is no sft_InternLM_XC.sh in the scripts. Therefore I want to check if the repo support for SFT InternLM-XComposer2.
Thank you!