Update README.md

README.md

@@ -31,12 +31,12 @@ In the following table, we provide all models [🤗 link] of the TokenOCR series
 |  [R50]()  |  Backbone is ResNet-50   |
 |  [TokenOCR-2048-Bilingual-seg]()  |  feature dimension is 2048; support interactive with English and Chinese texts. |
 | [TokenOCR-4096-English-seg](https://huggingface.co/TongkunGuan/TokenOCR_4096_English_seg) | feature dimension is 2048; only support interactive with English texts (We recommend).  |
-
+</center>
 
 ### Quick Start
 
-<!-- > \[!Warning\]
-> 🚨 Note: In our experience, the `TokenOCR-2048-Bilingual` series is better suited for building MLLMs than the `-seg` version. -->
+> \[!Warning\]
+> 🚨 Note: Since there are fewer Chinese images in public data than English, we recommend you use the **`TokenOCR-4096-English-seg`** version.
 
 ```python
 import os
@@ -87,8 +87,7 @@ generate_similiarity_map(images, attn_map, all_bpe_strings, out_dir, target_aspe
 """user command """
 # python quick_start.py
 ```
-
-
+<center>
 
 <!-- # Introduction -->
 <h2 style="color: #4CAF50;">Introduction</h2>