deepseek-ai /
DeepSeek-OCR
Contexts Optical Compression
Updated 35 min ago
+44 stars gained this week
Stars gained each day, last 30 days
Usual pace · 8 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
DeepSeek-OCR is a model for optical text compression, turning document images into compact vision tokens for LLM-based OCR. It is aimed at researchers and developers working on visual-text compression and document understanding.
Summary written by AI from the repository’s description and README.
deepseek-ai / DeepSeek-OCR
View on GitHub(opens in new tab)