CoolFace
Modelpublic

stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step150

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes17downloads
filemodel-00001-of-00004.safetensors4.54 GBdownload
filemodel-00002-of-00004.safetensors4.59 GBdownload
filemodel-00003-of-00004.safetensors4.03 GBdownload
filemodel-00004-of-00004.safetensors1.02 GBdownload

stellalisy/rethink_rlvr_reproduce-majority_vote-qwen2.5_math_7b-lr5e-7-kl0.00-step150 · main · files are served by the source, never re-hosted here