Add license, link to paper, and GitHub repo

README.md

@@ -1,10 +1,12 @@
 ---
 datasets:
 - Lin-Chen/ShareGPT4V
-pipeline_tag: image-text-to-text
 library_name: xtuner
+pipeline_tag: image-text-to-text
+license: apache-2.0
 ---
 
+```markdown
 <div align="center">
   <img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>
 
@@ -14,6 +16,10 @@ library_name: xtuner
 
 </div>
 
+The weights in this repository are from the paper [Magic 1-For-1: Generating One Minute Video Clips within One Minute](https://huggingface.co/papers/2502.07701).
+
+Github repository: https://github.com/DA-Group-PKU/Magic-1-For-1.
+
 ## Model
 
 llava-llama-3-8b-v1_1-hf is a LLaVA model fine-tuned from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) and [CLIP-ViT-Large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) with [ShareGPT4V-PT](https://huggingface.co/datasets/Lin-Chen/ShareGPT4V) and [InternVL-SFT](https://github.com/OpenGVLab/InternVL/tree/main/internvl_chat#prepare-training-datasets) by [XTuner](https://github.com/InternLM/xtuner).
@@ -120,3 +126,4 @@ Please refer to [docs](https://github.com/InternLM/xtuner/tree/main/xtuner/confi
     year={2023}
 }
 ```
+```