Wigtn/Qwen3-VL-2B-WigtnOCR
Image-Text-to-Text • 2B • Updated • 393 • 2
None defined yet.
Hi! We are WIGTN, an open-source AI research crew.
We build practical, domain-specialized AI tools — starting with document intelligence for Korean public sector documents. Our first release is WigtnOCR, a VLM-based document parser fine-tuned for Korean government documents.
Feel free to check out our website and try our latest models!