CoolFace
Modelpublic

zbeeb/Qwen2.5-Math-1.5B-GRPO-Staleness-8

sourceHugging Faceapache-2.0updated 9d agoView on Hugging Face
0likes289downloads
2 commits on main
38c52689d ago

Publish verified step-1000 GRPO checkpoint, staleness cap 8

zbeeb
ae32dd49d ago

initial commit

zbeeb