Update README.md

README.md

@@ -50,7 +50,7 @@ Please see our [paper](TODO) for more details on the evaluation setup.
 | DeepSeek-R1                   | 79.1 (86.7)     | 64.3 (73.3) | 53.0 (59.2) | 10.5 (11.4) |
 
 We used [a version of OpenMath-Nemotron-14B](https://huggingface.co/nvidia/OpenMath-Nemotron-14B-Kaggle) model to secure 
-the first place in AIMO-2 Kaggle competition!
+the first place in [AIMO-2 Kaggle competition](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/leaderboard)!
 
 ## Reproducing our results
 
@@ -73,7 +73,7 @@ To run inference with CoT mode, you can use this example code snippet.
 import transformers
 import torch
 
-model_id = "nvidia/OpenMath-Nemotron-1.5B"
+model_id = "nvidia/OpenMath-Nemotron-14B"
 
 pipeline = transformers.pipeline(
     "text-generation",