Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch.
-
lomahony/eleuther-pythia160m-hh-sft
Text Generation • 0.2B • Updated • 27 -
lomahony/eleuther-pythia2.8b-hh-sft
Text Generation • Updated • 290 • 1 -
lomahony/eleuther-pythia410m-hh-sft
Text Generation • Updated • 181 -
lomahony/eleuther-pythia6.9b-hh-dpo
Text Generation • Updated • 176