Modelpublic

sandeep123/aops-grpo-temp12-step900

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes31downloads

3 commits on main

904b35e25d ago

Correct model card: per-dataset settings (previous card was hardcoded for ScienceQA)

sandeep123

1c2b27227d ago

aops_grpo_temp12 step 900 | pass@1 0.2298 pass@6 0.4258 | best pass@6

sandeep123

55f66aa27d ago

initial commit

sandeep123