Modelpublic

sandeep123/aops-grpo-temp12-step600

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes30downloads

3 commits on main

fd31e8e25d ago

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

sandeep123

d87a1b227d ago

aops_grpo_temp12 step 600 | pass@1 0.2298 pass@6 0.4180 | best pass@6

sandeep123

1a87b9c27d ago

initial commit

sandeep123