Add metadata and link to paper

This PR improves the model card by adding relevant metadata:
- **Pipeline Tag**: `image-text-to-text` for multimodal capabilities.
- **Library Name**: `transformers` (the model includes an `auto_map` in `config.json`).
- **License**: `other` (Yuan 3.0 Model License Agreement).

It also ensures the model is correctly associated with the research paper [Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications](https://huggingface.co/papers/2601.01718).

README.md

@@ -1,3 +1,9 @@
+---
+license: other
+library_name: transformers
+pipeline_tag: image-text-to-text
+---
+
 <div align="center">
 <h1>
   Yuan 3.0 Multimodal Foundation Model
@@ -33,7 +39,7 @@
 
 ## 1. Introduction
 
-Yuan 3.0 Flash, developed by the **YuanLab.ai team**, is a **40B parameter multimodal foundation model** that employs a Mixture of Experts (MoE) architecture, activating only approximately **3.7B parameters** per inference. Through innovative reinforcement learning training methods (RAPO), it significantly reduces inference token consumption while improving reasoning accuracy, exploring the innovative path of "less computation, higher intelligence" for large language models. We have also released the <a href="https://arxiv.org/abs/2601.01718" target="_blank">**technical report**</a> for the Yuan3.0 model, where you can find more detailed technical information and evaluation results.
+Yuan 3.0 Flash, developed by the **YuanLab.ai team**, is a **40B parameter multimodal foundation model** that employs a Mixture of Experts (MoE) architecture, activating only approximately **3.7B parameters** per inference. Through innovative reinforcement learning training methods (RAPO), it significantly reduces inference token consumption while improving reasoning accuracy, exploring the innovative path of "less computation, higher intelligence" for large language models. We have also released the [**technical report**](https://huggingface.co/papers/2601.01718) for the Yuan3.0 model, where you can find more detailed technical information and evaluation results.
 
 <div align="center">
   <img src="https://huggingface.co/YuanLabAI/Yuan3.0-Flash-4bit/resolve/main/docs/Yuan3.0-architecture.png" width="80%" />
@@ -55,7 +61,7 @@ Yuan 3.0 Flash outperforms GPT-5.1 in enterprise-grade RAG, multimodal retrieval
 
 <div align="center">
   <img src="https://huggingface.co/YuanLabAI/Yuan3.0-Flash-4bit/resolve/main/docs/Yuan3.0-benchmarks.png" width="80%" />
-Fig.1: Yuan3.0 Multimodal Large Language Model Architecture
+Fig.2: Yuan3.0 Flash Evaluation Results
 </div>
 
 
@@ -177,4 +183,5 @@ Summarization generation is a core requirement for historical information compre
 | **OpenAI GPT-5.1** | 49.44 | 27.48 | 10.16 | 84.63 | 40.50 |
 | **Yuan3.0 Flash** | **59.31** | 51.32 | 28.32 | 89.99 | 45.34 |
 
-
+## 6. License Agreement
+The use of Yuan 3.0 code and models must comply with the [《Yuan 3.0 Model License Agreement》](https://github.com/Yuan-lab-LLM/Yuan3.0?tab=License-1-ov-file). The Yuan 3.0 model supports commercial use without requiring authorization application. Please understand and comply with the agreement, and do not use the open-source model and code, as well as derivatives generated based on the open-source project, for any purpose that may bring harm to the country and society, or for any service that has not undergone security assessment and filing.