Replace Arxiv link with paper page link

README.md

@@ -2,12 +2,12 @@
 base_model:
 - mistralai/Mistral-7B-v0.1
 - m-a-p/MERT-v1-95M
-library_name: peft
-license: apache-2.0
 datasets:
 - amaai-lab/MusicBench
 language:
 - en
+library_name: peft
+license: apache-2.0
 metrics:
 - bertscore
 - bleu
@@ -20,7 +20,7 @@ SonicVerse is a multi-task music captioning model that integrates caption genera
 
 View **demo** on [our HuggingFace Space](https://huggingface.co/spaces/amaai-lab/SonicVerse)
 
-**Read the paper:** [SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning](https://arxiv.org/abs/2506.15154)
+**Read the paper:** [SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning](https://huggingface.co/papers/2506.15154)
 
 **GitHub:** [https://github.com/AMAAI-Lab/SonicVerse](https://github.com/AMAAI-Lab/SonicVerse)
 
@@ -47,4 +47,4 @@ If you use SonicVerse, please cite our [paper](https://doi.org/10.48550/arXiv.25
 }
 ```
 
-DOI: [10.48550/arXiv.2506.15154](https://doi.org/10.48550/arXiv.2506.15154)
+DOI: [10.48550/arXiv.2506.15154](https://doi.org/10.48550/arXiv.2506.15154)