Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch.
Laura O'Mahony
lomahony
AI & ML interests
PhD student
Organizations
None yet
Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch.
Pythia-2.8b supervised finetuned and DPO finetuned with the helpful subset of Anthropic-hh-rlhf dataset for 1 epoch.
Pythia-2.8b supervised finetuned and DPO finetuned with the helpful subset of Anthropic-hh-rlhf dataset for a second epoch.