Modelpublic

unconst/Affine-5czsc2fc98-r498-offline-dpo-hialpha-midrank-lobeta-softctx-extrasteps-merged

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes25downloads

3 commits on main

1a415961mo ago

R498 Offline-DPO merged SKIP_LOCAL_TKC p3220 (not a submission)

unconst

9c334771mo ago

R498 marsplan Offline-DPO merged salvage (TTL insurance; not a submission)

unconst

f4eba471mo ago

initial commit

unconst