Improve model card: add metadata, paper and GitHub links

README.md

@@ -1,7 +1,18 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: feature-extraction
+---
+
 # AuroLA
-This repo contains the checkpoint of the following paper:
 
-**Scaling Audio-Text Retrieval with Multimodal Large Language Model**
+This repository contains the checkpoint of the following paper:
+
+**[Scaling Audio-Text Retrieval with Multimodal Large Language Models](https://huggingface.co/papers/2602.18010)**
+
+AuroLA is a novel contrastive language-audio pre-training framework that re-purposes Multimodal Large Language Models (MLLMs) as a unified backbone for retrieval. It utilizes a scalable data pipeline, adapts an MLLM for retrieval by prompting it to summarize audio/text inputs, and uses a bidirectional re-ranking module for refined cross-modal interaction.
+
+Code: [https://github.com/Jazzcharles/AuroLA](https://github.com/Jazzcharles/AuroLA)
 
 ## Quick Start 
 
@@ -97,7 +108,8 @@ text_messages = [
     [
         {
             "role": "user",
-            "content": [{"type": "text", "text": f"{t}\nSummarize above sentence in one word:"}],
+            "content": [{"type": "text", "text": f"{t}
+Summarize above sentence in one word:"}],
         },
         {
             "role": "assistant",