---
title: naver-clova-ix/donut-base-finetuned-docvqa
description: Donut model fine-tuned on DocVQA. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first rele. Encoder-Decoder, 110M parameters.
canonical_url: https://superlinked.com/models/naver-clova-ix-donut-base-finetuned-docvqa
last_updated: 2026-06-08
---

# naver-clova-ix/donut-base-finetuned-docvqa

Donut model fine-tuned on DocVQA. It was introduced in the paper OCR-free Document Understanding Transformer by Geewok et al. and first released in this repository.

Source: [naver-clova-ix/donut-base-finetuned-docvqa on HuggingFace](https://huggingface.co/naver-clova-ix/donut-base-finetuned-docvqa)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Encoder-Decoder |
| Parameters | 110M |
| Tasks | Extract |
| Outputs | text_regions |
| License | mit |
| Inputs | image |

## Benchmarks

### DocVQA

Domain: general · Task: kie · Language: en

Visual question answering on document images

Corpus: 5,188 · Queries: 5,188

**Quality:** anls: 0.6350

[Reference](https://www.docvqa.org/)