QwenLM/online_merging_optimizers
Implementations of online merging optimizers proposed by Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
PythonApache-2.0
Stargazers
- CarryChangBytes Inc.
- ccclyuPalo Alto
- chchch0109
- chuanmingliuWesteros
- dubytang
- dumpmemory
- e0397123National University of Singapore (ECE-HLT)
- Emperorizzis
- fly51flyPRIS
- fredbjer
- GanjinZeroDAMO Academy
- gm8xx8
- hhhh12345678
- hiyougaMillennium Science School
- HkkSimple
- ioo0sLi Auto
- jn2clark
- kunatoKUNANA AI
- kylezhangwei
- lu-m13Intel Labs China
- Lukeming-tsinghuaQwen
- mingkinXiamen University
- MoonRide303Poland
- Phantasmal77
- puppet101
- RicardokevinsNanjing University
- shuxiaokaiM78 Nebula
- Trangle
- wangdh1027
- WangRongshengMacao Polytechnic University
- wengrxNanjing University
- whr94621Nanjing University
- yangapkuPeking Univ.
- yubowen-phChinese Academy of Sciences
- yunhenkHangZhou
- ZhuochengZhang98University of Chinese Academy of Sciences