Improve model card: Add `library_name` and update paper link

README.md

@@ -1,16 +1,18 @@
 ---
-license: mit
+base_model:
+- Qwen/Qwen2.5-VL-7B-Instruct
 datasets:
 - Kwai-Keye/Thyme-SFT
 - Kwai-Keye/Thyme-RL
 language:
 - en
+license: mit
 metrics:
 - accuracy
-base_model:
-- Qwen/Qwen2.5-VL-7B-Instruct
 pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+
 <div align="center">
   <img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/dxBp6TmwqwNuBuJR9gfQC.png" width="40%" alt="Thyme Logo">
 </div>
@@ -18,7 +20,7 @@ pipeline_tag: image-text-to-text
 <font size=4><div align='center' >  
 [[📖 Home Page](https://thyme-vl.github.io/)] 
 [[📖 Github Repo](https://github.com/yfzhang114/Thyme)] 
-[[📖 Technique Report](https://arxiv.org/abs/2508.11630)] 
+[[📖 Paper](https://huggingface.co/papers/2508.11630)] 
 
 [[📊 Thyme SFT Model](https://huggingface.co/Kwai-Keye/Thyme-SFT)] 
 [[📊 Thyme RL Model](https://huggingface.co/Kwai-Keye/Thyme-RL)] 
@@ -27,7 +29,7 @@ pipeline_tag: image-text-to-text
 </div></font>
 
 ## 🔥 News
-* **`2025.08.15`** 🌟 We are excited to introduce **Thyme: Think Beyond Images**. Thyme transcends traditional ``thinking with images'' paradigms by autonomously generating and executing diverse image processing and computational operations through executable code, significantly enhancing performance on high-resolution perception and complex reasoning tasks. Leveraging a novel two-stage training strategy that combines supervised fine-tuning with reinforcement learning and empowered by the innovative GRPO-ATS algorithm, Thyme achieves a sophisticated balance between reasoning exploration and code execution precision.
+* **`2025.08.15`** 🌟 We are excited to introduce **Thyme: Think Beyond Images**. Thyme transcends traditional ``thinking with images'' paradigms by autonomously generating and executing diverse image processing and computational operations through executable code, significantly enhancing performance on high-resolution perception and complex reasoning tasks. Leveraging a novel two-stage training strategy that combines supervised fine-tuning with reinforcement learning and empowered by the innovative GRPO-ATS algorithm, Thyme achieves a sophisticated balance between reasoning exploration with code execution precision.
 
 <div align="center">
   <img src="https://cdn-uploads.huggingface.co/production/uploads/685ba798484e3233f5ff6f11/c_D7uX3RT1WUANDRB70ZC.png" width="100%" alt="Thyme Logo">