Modelpublic

sandeep123/aops-grpo-vanilla-step800

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes25downloads

3 commits on main

f5ce81625d ago

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

sandeep123

c0c1b3927d ago

aops_grpo_vanilla step 800 | pass@1 0.2305 pass@6 0.4336 | best pass@6

sandeep123

385e5f627d ago

initial commit

sandeep123