Better aligned models obtained by weak-to-strong model extrapolation (ExPO)
-
Weak-to-Strong Extrapolation Expedites Alignment
Paper • 2404.16792 • Published • 11 -
chujiezheng/Mistral7B-PairRM-SPPO-ExPO
Text Generation • Updated • 5.11k -
chujiezheng/Smaug-34B-v0.1-ExPO
Text Generation • Updated • 2.85k -
chujiezheng/LLaMA3-iterative-DPO-final-ExPO
Text Generation • Updated • 797 • 2