Modelpublic

sandeep123/aops-grpo-cliphigh-step100

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes24downloads

3 commits on main

63c6aac25d ago

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

sandeep123

9aaf4fe27d ago

aops_grpo_cliphigh step 100 | pass@1 0.2135 pass@6 0.4219 | best pass@6

sandeep123

82d890127d ago

initial commit

sandeep123