Update README.md

README.md

@@ -34,6 +34,8 @@ We are excited to introduce  **Vintern-1B-v2** the Vietnamese 🇻🇳 multimoda
 
 [**\[🤗 HF Demo\]**](https://huggingface.co/spaces/khang119966/Vintern-v2-Demo)
 
+The special thing is that our model can be easily finetuned with a T4 GPU on Google Colab by following the instructions provided at the end of this section.
+
 ## Model Details
 
 |      Model Name      |                                     Vision Part                                     |                                        Language Part                                         |                  
@@ -55,7 +57,7 @@ Since there are still many different metrics that need to be tested, **we chose
 <table border="1" cellspacing="0" cellpadding="5">
     <tr align="center">
         <td rowspan="2"><b>Model</b></td>
-        <td colspan="2"><b>Gpt4o-Score</b></td>
+        <td colspan="2"><b>gpt4o-score</b></td>
     </tr>
     <tr align="center">
         <td><b>OpenViVQA-dev</b></td>