Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ license: apache-2.0
|
|
| 14 |
|
| 15 |
**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.
|
| 16 |
|
|
|
|
|
|
|
| 17 |
# Quick Start with vLLM
|
| 18 |
|
| 19 |
You can easily do inference using vLLM:
|
|
|
|
| 14 |
|
| 15 |
**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.
|
| 16 |
|
| 17 |
+
For advanced usage examples, see https://github.com/MoonshotAI/Kimina-Prover-Preview/tree/master/kimina_prover_demo
|
| 18 |
+
|
| 19 |
# Quick Start with vLLM
|
| 20 |
|
| 21 |
You can easily do inference using vLLM:
|