Better aligned models obtained by weak-to-strong model extrapolation (ExPO)
-
Weak-to-Strong Extrapolation Expedites Alignment
Paper • 2404.16792 • Published • 11 -
chujiezheng/Smaug-Llama-3-70B-Instruct-ExPO
Text Generation • Updated • 747 • 2 -
chujiezheng/Smaug-34B-v0.1-ExPO
Text Generation • Updated • 2.83k -
chujiezheng/Starling-LM-7B-beta-ExPO
Text Generation • Updated • 678 • 2