---
language:
- en
license: apache-2.0
benchmarks:
- ChatDoc/OCRFlux-bench-single
- ChatDoc/OCRFlux-bench-cross
- ChatDoc/OCRFlux-pubtabnet-single
- ChatDoc/OCRFlux-pubtabnet-cross
base_model:
- Qwen/Qwen2.5-VL-3B-Instruct
library_name: transformers
---


# OCRFlux

This is a preview release of the OCRFlux model that's fine tuned from Qwen2.5-VL-3B-Instruct using the our private document datasets and some data from
[olmOCR-mix-0225](https://huggingface.co/datasets/allenai/olmOCR-mix-0225) dataset.

Quick links:
- 🛠️ [Code](https://github.com/chatdoc-com/OCRFlux)

## Usage

The best way to use this model is via the [OCRFlux toolkit](https://github.com/chatdoc-com/OCRFlux).
The toolkit comes with an efficient inference setup via vllm that can handle millions of documents
at scale.

## License and use

OCRFlux is licensed under the Apache 2.0 license.
OCRFlux is intended for research and educational use.