CoolFace
Modelpublic

zjhhhh/efficient-reasoning-rloo-qwen3-1.7b-base-math12k-from-maxrl-step100-plus50-step_50

sourceHugging Faceupdated 1mo agoView on Hugging Face
0likes
root
dirglobal_step50/
file.gitattributes1 KBdownload
filetrain_config.json3 KBdownload

zjhhhh/efficient-reasoning-rloo-qwen3-1.7b-base-math12k-from-maxrl-step100-plus50-step_50 · main · files are served by the source, never re-hosted here