Update README.md

README.md

@@ -33,8 +33,16 @@ pinned: false
 
 <h2>Who are we?</h2>
 
+<p>Vietnamese Vision-Language Model (Vi-VLM) is a research project focusing on the multimodal field, integrating both vision and language for Vietnamese.</p>
+
+<p>Vi-VLM's research team wishes to contribute and develop the highest quality models and data sets to promote the development of Artificial Intelligence in the field of Vision-Language.</p>
+
 <h2>Current contribution</h2>
 
+<ol>
+  <li><a href="https://huggingface.co/datasets/Vi-VLM/Vista">Vista: Large dataset for vision-language built on LLAVA, ShareGPT4V, WIT.</a></li>
+</ol>
+
 <h2>Members</h2>
 
 <ul>