Add report link and benchmarks

README.md

@@ -9,7 +9,12 @@ base_model:
 pipeline_tag: document-question-answering
 library_name: transformers
 ---
-# Model Card for Model ID
+# Vintern-1B-v2-ViTable-docvqa
+
+<p align="center">
+  <a href="https://drive.google.com/file/d/1MU8bgsAwaWWcTl9GN1gXJcSPUSQoyWXy/view?usp=sharing"><b>Report Link</b>👁️</a>
+</p>
+
 
 <!-- Provide a quick summary of what the model is/does. -->
 Vintern-1B-v2-ViTable-docvqa is a fine-tuned version of the 5CD-AI/Vintern-1B-v2 multimodal model for the Vietnamese DocVQA (Table data)
@@ -17,11 +22,21 @@ Vintern-1B-v2-ViTable-docvqa is a fine-tuned version of the 5CD-AI/Vintern-1B-v2
 
 ## Benchmarks
 
-To be developed later
+<div align="center">
+
+| Model                       | ANLS                   | Semantic Similarity    | MLLM-as-judge (Gemini) |
+|-----------------------------|------------------------|------------------------|------------------------|
+| Gemini 1.5 Flash            | 0.35                   | 0.56                   | 0.40                   |
+| Vintern-1B-v2               | 0.04                   | 0.45                   | 0.50                   |
+| Vintern-1B-v2-ViTable-docvq | **0.50**               | **0.71**               | **0.59**               |
+
+</div>
+
+<!-- Code benchmark: to be written later -->
 
-## Quickstart
+<!-- To be written later ## Usage
 
-To be developed later
+You can use this notebook <a href="https://colab.research.google.com/"> <img src="https://colab.research.google.com/img/colab_favicon_256px.png" width="30"></a> -->
 
 **Citation:**