Vintern-1B-v2-ViTable-docvqa Open-source Model - Free Support for Vietnamese Document Table Data Q&A

Vintern 1B V2 ViTable Docvqa

Developed by YuukiAsuna

A fine-tuned version of the 5CD-AI/Vintern-1B-v2 multimodal model for Vietnamese document question answering (tabular data)

Downloads 21

Release Time : 11/17/2024

Model Overview

A multimodal model optimized for Vietnamese tabular data document question answering tasks

Optimized for Vietnamese table document QA

Fine-tuned specifically for Vietnamese tabular data document question answering tasks

Multimodal capability

Combines visual and language understanding to process tabular documents

Performance improvement

Significant improvements in ANLS and semantic similarity metrics compared to the base model

Table document understanding

Vietnamese question answering

Multimodal data processing

Document visual question answering

Document processing

Vietnamese tabular data QA

Extract information from Vietnamese tabular documents and answer questions

ANLS score 0.50, semantic similarity 0.71

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-docvqa	0.50	0.71	0.59

Property	Details
Model Type	Fine-tuned multimodal model for Vietnamese DocVQA (Table data)
Training Data	YuukiAsuna/VietnameseTableVQA
Base Model	5CD-AI/Vintern-1B-v2
Pipeline Tag	document-question-answering
Library Name	transformers

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base