Modelpublic

sandeep123/aops-grpo-vanilla-step100

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes25downloads

3 commits on main

85f7c9525d ago

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

sandeep123

aec03e727d ago

aops_grpo_vanilla step 100 | pass@1 0.2259 pass@6 0.4336 | best pass@6

sandeep123

edab4e027d ago

initial commit

sandeep123