Replace Arxiv link with paper page link

README.md

@@ -1,10 +1,10 @@
 ---
-library_name: transformers
-license: mit
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-Math-1.5B-Instruct
+language:
+- en
+library_name: transformers
+license: mit
 pipeline_tag: text-generation
 ---
 
@@ -12,8 +12,6 @@ pipeline_tag: text-generation
 
 This model is fine-tuned using self-training methods to generate concise reasoning paths for reasoning tasks while maintaining accuracy.
 
-
-
 ## Model Details
 
 - **Developed by:** Tergel Munkhbat, Namgyu Ho, Seo Hyun Kim, Yongjin Yang, Yujin Kim, Se-Young Yun at KAIST AI
@@ -22,7 +20,7 @@ This model is fine-tuned using self-training methods to generate concise reasoni
 - **License:** MIT
 - **Finetuned from model:** Qwen/Qwen2.5-Math-1.5B-Instruct
 - **Repository:** https://github.com/TergelMunkhbat/concise-reasoning
-- **Paper:** [Self-Training Elicits Concise Reasoning in Large Language Models](https://arxiv.org/abs/2502.20122)
+- **Paper:** [Self-Training Elicits Concise Reasoning in Large Language Models](https://huggingface.co/papers/2502.20122)
 
 ## How to Get Started with the Model
 
@@ -49,7 +47,7 @@ response = tokenizer.decode(outputs[0][input_length:], skip_special_tokens=True)
 print(response)
 ```
 
-For more detailed information about training methods, evaluation results, limitations, and technical specifications, please refer to our [paper](https://arxiv.org/abs/2502.20122).
+For more detailed information about training methods, evaluation results, limitations, and technical specifications, please refer to our [paper](https://huggingface.co/papers/2502.20122).
 
 ## Citation