xiaomi-research / Xiaomi-OCR-0
Vision873M17.1K206Updated Oct 29, 2026
Downloads
17.1K
Likes
206
Last updated
Oct 29, 2026
License
apache-2.0
Xiaomi-OCR-0 is a unified 0.8B OCR-specialized vision-language model for both document parsing and OCR-centric understanding.
Tasks & library
- image text to text
- transformers
Tags
- transformers
- qwen3_5
- image-text-to-text
- ocr
- document-parsing
- document-understanding
Technical specifications
Parameters873M
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen3.5-0.8B-Base
Licenseapache-2.0