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