Add library_name, paper and project page links

This PR enhances the model card by:
- Adding the `library_name: transformers` metadata tag, which enables the "How to use" widget on the Hugging Face Hub.
- Adding a direct link to the paper [MiDashengLM: Efficient Audio Understanding with General Audio Captions](https://huggingface.co/papers/2508.03983) in the main content.
- Including a link to the project page https://xiaomi-research.github.io/dasheng-lm/ in the main content.

Please review and merge if everything looks good.

README.md

@@ -1,25 +1,30 @@
 ---
-license: apache-2.0
+base_model:
+- mispeech/dasheng-0.6B
+- Qwen/Qwen2.5-Omni-7B
 language:
 - en
 - zh
 - th
 - id
 - vi
+license: apache-2.0
 pipeline_tag: audio-text-to-text
 tags:
 - multimodal
 - audio-language-model
 - audio
-base_model:
-- mispeech/dasheng-0.6B
-- Qwen/Qwen2.5-Omni-7B
 base_model_relation: finetune
+library_name: transformers
 ---
+
 # MiDashengLM-7B-0804 (4bit, GPTQ quantized)
 
 The 4bit (w4a16) weights for [mispeech/midashenglm-7b-0804-fp32](https://huggingface.co/mispeech/midashenglm-7b-0804-fp32), quantized by GPTQ.
 
+This model is described in the paper [MiDashengLM: Efficient Audio Understanding with General Audio Captions](https://huggingface.co/papers/2508.03983).
+For more details, visit the project page: https://xiaomi-research.github.io/dasheng-lm/
+
 An ideal choice for resource-constrained environments. It offers broad GPU compatibility and a smaller memory footprint, making it suitable for deployment where VRAM, memory, or storage is limited, provided that a slight trade-off in quality is acceptable.
 
 ## Usage