Modelpublic

sandeep123/aops-grpo-temp12-step400

sourceHugging Faceapache-2.0updated 26d agoView on Hugging Face

0likes26downloads

3 commits on main

3c8010626d ago

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

sandeep123

f51297d28d ago

aops_grpo_temp12 step 400 | pass@1 0.2363 pass@6 0.4023 | best pass@1

sandeep123

b53db3428d ago

initial commit

sandeep123