Update README.md

README.md

@@ -12,7 +12,7 @@ license: apache-2.0
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/66775fab8c58c5a12ae629ac/mtT1qq2bKycrWvy9NT0ly.png)
 
-**AI-MO/Kimina-Prover-Distill-8B** is a theorem proving model developed by Project Numina and Kimi teams, focusing on competition style problem solving capabilities in Lean 4. It is a distillation of **Kimina-Prover**, a model trained via large scale reinforcement learning. It achieves 77.86% accuracy with Pass@32 on MiniF2F-test.
+**AI-MO/Kimina-Prover-Distill-8B** is a theorem proving model developed by Project Numina and Kimi teams, focusing on competition style problem solving capabilities in Lean 4. It is a distillation of **Kimina-Prover-72B**, a model trained via large scale reinforcement learning. It achieves 77.86% accuracy with Pass@32 on MiniF2F-test.
 
 # Quick Start with vLLM