CoolFace
Modelpublic

zbeeb/Qwen2.5-Math-7B-GRPO-Staleness-4

sourceHugging Faceapache-2.0updated 5d agoView on Hugging Face
0likes108downloads
2 commits on main
05d099e5d ago

Publish verified step-1000 GRPO checkpoint, staleness cap 4

zbeeb
c7735075d ago

initial commit

zbeeb