---
license: mit
datasets:
- YuukiAsuna/VietnameseTableVQA
language:
- vi
base_model:
- 5CD-AI/Vintern-1B-v2
pipeline_tag: document-question-answering
library_name: transformers
---
# 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)


## Benchmarks

<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 -->

<!-- To be written later ## Usage

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:**

```bibtex
@misc{doan2024vintern1befficientmultimodallarge,
      title={Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese}, 
      author={Khang T. Doan and Bao G. Huynh and Dung T. Hoang and Thuc D. Pham and Nhat H. Pham and Quan T. M. Nguyen and Bang Q. Vo and Suong N. Hoang},
      year={2024},
      eprint={2408.12480},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2408.12480}, 
}
```