# Document Visual Question Answering

MLCD-ViT-bigG is an advanced Vision Transformer model enhanced with 2D Rotary Position Encoding (RoPE2D), excelling in document understanding and visual question answering tasks.

INT8 quantized version based on mgoin/pixtral-12b, supports vision-text multimodal tasks with optimized inference efficiency

Quantized version of Qwen/Qwen2.5-VL-3B-Instruct, supporting visual-text input and text output, with weights quantized to INT8 and activations quantized to INT8.

Florence-2 DocVQA is a document visual question answering model fine-tuned based on the Microsoft Florence-2-large model, specifically designed for handling question-answering tasks in document images.

UDOP is a universal document processing model that unifies vision, text, and layout, based on the T5 architecture, suitable for document AI tasks.

UDOP is a universal document processing model that unifies vision, text, and layout, based on the T5 architecture, suitable for tasks such as document image classification, parsing, and visual question answering.

A document visual question answering model based on the LayoutLMv2 architecture, fine-tuned for DocVQA tasks

Document question answering model fine-tuned based on LayoutLMv3-base, suitable for document visual question answering tasks

A document Q&A model based on the Donut architecture, capable of extracting text information from images and answering questions

A document visual question answering model based on the LayoutLMv2 architecture, fine-tuned specifically for document understanding tasks

A document visual question answering model based on the LayoutLMv2 architecture, specifically fine-tuned for document understanding tasks

Pix2Struct is an image encoder-text decoder model trained on image-text pairs, supporting various tasks including image captioning and visual question answering.

Pix2Struct is a vision-language model based on an image encoder-text decoder architecture, specifically fine-tuned for document visual question answering tasks

This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased for document visual question answering tasks, focusing on processing text and layout information in document images.

A document QA model fine-tuned based on the LayoutLM architecture, specifically designed for processing structured documents like invoices

Donut is an OCR-free document understanding Transformer model, fine-tuned on the DocVQA dataset, capable of directly extracting and comprehending text information from images.

A document visual question answering model fine-tuned based on microsoft/layoutlmv2-large-uncased, suitable for Vietnamese information extraction tasks

Document understanding model based on the LayoutLMv2 architecture, fine-tuned for InfoVQA tasks