# Document Image Understanding

FP8 quantized version of Qwen2.5-VL-72B-Instruct, supporting vision-text input and text output, optimized and released by Neural Magic.

A document OCR model fine-tuned based on Qwen2-VL-7B-Instruct, supporting multilingual document recognition and metadata extraction

The quantized version of Qwen2.5-VL-3B-Instruct, with weights quantized to INT4 and activations quantized to FP16, designed for efficient vision-text task inference.

The FP8 quantized version of Qwen2.5-VL-72B-Instruct, supporting vision-text input and text output, suitable for multimodal tasks.

Eagle2 is a high-performance series of vision-language models focused on enhancing model performance through optimized data strategies and training methods. Eagle2-9B is the large model in this series, achieving a good balance between performance and inference speed.

Eagle 2 is a high-performance vision-language model family that focuses on transparency in data strategies and training schemes, aiming to drive the open-source community in developing competitive vision-language models.

PaliGemma 2 is a multi-functional vision-language model (VLM) launched by Google, which combines image and text processing capabilities and supports multilingual and multi-task processing.

A version fine-tuned for 1 day using the Docmatix dataset (5% data volume) based on Microsoft's Florence-2 model, suitable for image-text understanding tasks

PaliGemma is a lightweight vision-language model developed by Google, built on the SigLIP vision model and the Gemma language model, supporting multilingual image-text understanding and generation.

Donut is an OCR-free document understanding Transformer model that combines a visual encoder and text decoder to process document images

A medical handwritten prescription information extraction model based on the Donut architecture, designed to extract structured information from medical prescription images

A model fine-tuned based on naver-clova-ix/donut-base, specific uses and functions require more information

A document understanding model fine-tuned from naver-clova-ix/donut-base, specialized in structured document information extraction tasks

A document understanding model fine-tuned from naver-clova-ix/donut-base, suitable for image folder datasets

A model fine-tuned on the image folder dataset based on naver-clova-ix/donut-base, suitable for document understanding tasks

A fine-tuned version based on the naver-clova-ix/donut-base model on an image folder dataset, suitable for document understanding tasks.