DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales.
Zhewei YaoReza Yazdani AminabadiOlatunji RuwaseSamyam RajbhandariXiaoxia WuAmmar Ahmad AwanJeff RasleyMinjia ZhangConglong LiConnor HolmesZhongzhu ZhouMichael WyattMolly SmithLev KurilenkoHeyang QinMasahiro TanakaShuai CheShuaiwen Leon SongYuxiong HePublished in: CoRR (2023)