CoolFace
Modelpublic

shawnmkim/qwen2.5-coder-7b-rlvr-compete-collab

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face
0likes10downloads
2 commits on main
29888223mo ago

Initial upload — RLVR/GRPO LoRA adapter (1000 steps, peak 8.8% at ckpt 250-750)

shawnmkim
48259bb3mo ago

initial commit

shawnmkim