DeepSeek OCR - More than OCR

In this video, I look at DeepSeek OCR and show that it's an experiment in using images to compress text representations better.

DeepSeek OCR Paper: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSeek_OCR_paper.pdf

For more tutorials on using LLMs and building agents, check out my Patreon
Patreon: https://www.patreon.com/SamWitteveen
Twitter: https://x.com/Sam_Witteveen

🕵️ Interested in building LLM Agents? Fill out the form below
Building LLM Agents Form: https://drp.li/dIMes

👨‍💻Github:
https://github.com/samwit/llm-tutorials

⏱️Time Stamps:
00:00 Intro
00:30 DeepSeek OCR: Contexts Optical Compression Paper
03:37 Transformer
04:12 Vision Transformer (ViT)
10:11 DeepSeek-OCR GitHub and Hugging Face
10:32 Nanonets and PaddleOCR-VL

Видео DeepSeek OCR - More than OCR канала Sam Witteveen