Modelpublic

unconst/Affine-5czsc2fc98-r482-offline-dpo-hialpha-midrank-extrasteps-merged

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes18downloads

3 commits on main

cdca1521mo ago

R482 marsplan Offline-DPO merged salvage (TTL insurance; not a submission)

unconst

bbe92bc1mo ago

R482 Offline-DPO merged SKIP_LOCAL_TKC p3220 (not a submission)

unconst

0c4f03d1mo ago

initial commit

unconst