CoolFace
Modelpublic

shengjia-toronto/sac-gspo-cl5e3-drgrpo-llama32-3b-deepscaler-step881-best-pass1-16.34-8xH200

sourceHugging Faceupdated 4mo agoView on Hugging Face
0likes5downloads
filemodel-00001-of-00002.safetensors4.66 GBdownload
filemodel-00002-of-00002.safetensors2.06 GBdownload

shengjia-toronto/sac-gspo-cl5e3-drgrpo-llama32-3b-deepscaler-step881-best-pass1-16.34-8xH200 · main · files are served by the source, never re-hosted here