Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data
-
OpenBezoar: Small, Cost-Effective and Open Models Trained on Mixes of Instruction Data
Paper • 2404.12195 • Published • 12 -
SurgeGlobal/OpenBezoar-SFT
Text Generation • 3B • Updated • 23 • 3 -
SurgeGlobal/OpenBezoar-HH-RLHF-SFT
Text Generation • 3B • Updated • 42 -
SurgeGlobal/OpenBezoar-HH-RLHF-DPO
Text Generation • 3B • Updated • 34