Modelpublic

ianlee1996/pokerbench-qwen3-14b-lora-8max-dpo-selfraise

sourceHugging Faceupdated 2mo agoView on Hugging Face

0likes13downloads

2 commits on main

e361d652mo ago

self_raise_count-fix cycle DPO retrain (Stage A eval in progress, not yet validated)

ianlee1996

33706ce2mo ago

initial commit

ianlee1996