---
title: mynkchaudhry/Florence-2-FT-DocVQA
description: This model card provides details about the Florence-2-FT-DocVQA model, which is fine-tuned for Document Visual Question Answering (VQA) task. Florence-2, 271M parameters.
canonical_url: https://superlinked.com/models/mynkchaudhry-florence-2-ft-docvqa
last_updated: 2026-06-15
---

# mynkchaudhry/Florence-2-FT-DocVQA

This model card provides details about the Florence-2-FT-DocVQA model, which is fine-tuned for Document Visual Question Answering (VQA) tasks.

Source: [mynkchaudhry/Florence-2-FT-DocVQA on HuggingFace](https://huggingface.co/mynkchaudhry/Florence-2-FT-DocVQA)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Florence-2 |
| Parameters | 271M |
| Tasks | Extract |
| Outputs | text_regions |
| License | apache-2.0 |
| Inputs | text, image |
| Languages | en |

## Benchmarks

### DocVQA

Domain: general · Task: kie · Language: en

Visual question answering on document images

Corpus: 5,188 · Queries: 5,188

**Quality:** anls: 0.3521 · exact match: 0.2600

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