openpsi-project/ReaLHF
Super-Efficient RLHF Training of LLMs with Parameter Reallocation
PythonApache-2.0
Stargazers
- AIRobotZhangInstitute of Information Engineering, CAS
- Anson529
- chaojin0310Peking University
- devjerry0PMG
- DWCTOD
- Dylancer1998China
- foreverpianoTHU菜鸡
- Freja71122
- garrett4wadeTsinghua University
- ipruningEdinburgh, UK ⇌ Shanghai, China
- IrisLi17Tsinghua University
- kessmith
- lixsh6
- Misakamikoto527CSU
- moclimb
- nowhereSpace
- PKUFlyingPigPeking University
- raniprati
- RunxinXuPeking University
- ryokTokyo, Japan
- samjia2000
- shaunrfieldAuckland
- SoftwareGift
- tangh18Tsinghua University
- UltronAITsinghua University
- war40870527951job
- WhaoooooTsinghua University
- wyooyw
- xssstory
- yml-blog
- Yuang-DengShanghai Jiao Tong University
- zesen01Hangzhou China
- zhanghb55Sun Yat-sen University
- zhimin-zSoftware Analysis and Intelligence Lab
- zhxiemlSJTU
- zldscr0