# Structured Extraction

Donut is a Transformer-based document understanding model specifically designed for document question-answering tasks.

Donut is a Transformer-based image-to-text model capable of extracting and generating textual content from images.

An instruction fine-tuned model based on Llama3-8B, trained on over 2,750 datasets, suitable for various NLP tasks

This model is outdated. It is recommended to use the official Nougat model. Nougat is an advanced vision-language model focused on document understanding and analysis.

A BERT-based named entity recognition model for the Chinese medical domain, capable of identifying professional entities in medical texts.

Invoice recognition model based on Donut architecture, fine-tuned on a dataset of 200 invoices

A fine-tuned version of the microsoft/layoutlmv2-base-uncased model on an unknown dataset, suitable for document understanding tasks