Modelpublic

sandeep123/aops-grpo-entropy-step800

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes27downloads

3 commits on main

5f2274f25d ago

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

sandeep123

d2b895a27d ago

aops_grpo_entropy step 800 | pass@1 0.2298 pass@6 0.4023 | best pass@1

sandeep123

e797eb227d ago

initial commit

sandeep123