Modelpublic

zbeeb/Qwen2.5-3B-GRPO-Staleness-4

sourceHugging Faceotherupdated 9d agoView on Hugging Face

0likes340downloads

2 commits on main

fda75b99d ago

Publish verified step-1000 GRPO checkpoint, staleness cap 4

zbeeb

fd268a49d ago

initial commit

zbeeb