Update README.md

README.md

@@ -5,6 +5,9 @@ base_model: TokenOCR
 base_model_relation: finetune
 ---
 
+# A Token-level Text Image Foundation Model for Document Understanding
+
+
 [\[📂 GitHub\]](https://github.com/Token-family/TokenOCR)    [\[📖 Paper\]]() [\[🆕 Blog\]]()    [\[🤗 HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL)    [\[🚀 Quick Start\]](#quick-start)  
 
 <div align="center">
@@ -22,7 +25,8 @@ we seamlessly replace previous VFMs with TokenOCR to construct a document-level
 
 # Token Family
 
-## TokenIT
+<!-- ## TokenIT -->
+<h2 style="color: #4CAF50;">TokenIT</h2>
 
 In the following picture, we provide an overview of the self-constructed token-level **TokenIT** dataset, comprising 20 million images and 1.8 billion
 text-mask pairs. 
@@ -50,7 +54,9 @@ The comparisons with other visual foundation models:
 | **TokenOCR**           | **token-level** | **TokenIT**  | **20M**    | **1.8B**   |
 
 
-## TokenOCR
+<!-- ## TokenOCR
+ -->
+<h2 style="color: #4CAF50;">TokenOCR</h2>
 
 ### Model Architecture
 
@@ -136,7 +142,8 @@ Please refer to our technical report for more details.
 
 <!-- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/650d4a36cbd0c7d550d3b41b/IbLZ0CxCxDkTaHAMe7M0Q.png)
  -->
-## TokenVL
+<!-- ## TokenVL -->
+<h2 style="color: #4CAF50;">TokenVL</h2>
 
 we employ the TokenOCR as the visual foundation model and further develop an MLLM, named TokenVL, tailored for document understanding. 
 Following the previous training paradigm, TokenVL also includes two stages: