CoolFace
Modelpublic

ermiaazarkhalili/Qwen3-1.7B-GRPO-NuminaMath-10K

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes19downloads
2 commits on main
52a92733mo ago

GRPO NuminaMath-CoT (10K) LoRA adapter — recovered push (adapter files only)

ermiaazarkhalili
2fe745a3mo ago

initial commit

ermiaazarkhalili