CoolFace
Modelpublic

MusaKlair/pythia410m-dpo-beta0.1

sourceHugging Faceupdated 3mo agoView on Hugging Face
0likes21downloads
6 commits on main
da0e3ba3mo ago

Update log_history.json with full 3-epoch history

MusaKlair
dd005553mo ago

DPO fine-tuned pythia-410m, beta=0.1 (3 epochs)

MusaKlair
68b49c43mo ago

Upload checkpoint-189 for beta=0.1

MusaKlair
1fb19923mo ago

Upload checkpoint-100 for beta=0.1

MusaKlair
437ac8a3mo ago

DPO fine-tuned pythia-410m, beta=0.1

MusaKlair
7d9f10c3mo ago

initial commit

MusaKlair