AIbase
EN
Home
Donut Finetune Rvl Cdip
D

Donut Finetune Rvl Cdip

Developed by sitloboi2012
Document classification model based on the Donut framework, trained on a small-scale RVL-CDIP dataset
Image-to-Text
Transformers
 EnglishOpen Source License:Apache-2.0#End-to-end document classification#Few-shot training#Image-to-text conversion
Downloads 18
Release Time : 9/30/2023

Model Overview

This model adopts the Donut framework and VisionEncoderDecoder architecture, specifically designed for end-to-end document classification tasks, suitable for processing English document images.

Model Features

End-to-end document classification
Directly processes image inputs and outputs classification results without separate OCR steps
Small-scale dataset training
Trained on a 100-image subset of RVL-CDIP, suitable for rapid validation and benchmarking
Based on the Donut framework
Utilizes advanced vision-language model architecture for document AI tasks

Model Capabilities

Document image classification
English document processing
End-to-end image-to-text conversion

Use Cases

Document management
Food document classification
Automatically identifies and categorizes food-related documents
Financial document processing
Classifies financial documents such as invoices and receipts
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase