---
title: TinyDoc-VLM Demo
emoji: 📄
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.50.0
app_file: app.py
pinned: true
license: apache-2.0
tags:
  - demo
  - document-understanding
  - ocr
  - vqa
  - vision-language-model
  - tinyml
  - gradio
---

# TinyDoc-VLM Demo

Upload an invoice, receipt, form, or table and ask questions. **256M-param document AI** that runs on CPU.

**Try it:**
1. Upload a document image
2. Ask a question (e.g., "What is the total?", "Extract all fields")
3. Get structured answers

## Links

- [GitHub](https://github.com/eulogik/TinyDoc-VLM)
- [PyPI](https://pypi.org/project/tinydoc/)
- [Model Hub](https://huggingface.co/eulogik/TinyDoc-VLM-256M)
- [LoRA Adapter](https://huggingface.co/eulogik/TinyDoc-VLM-LoRA)

## What can it do?

- Invoice processing
- Receipt scanning
- Form understanding
- Table extraction
- Document Q&A
- OCR