Paper - https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSeek_OCR_paper.pdf
Become AI Researcher & Train LLM From Scratch - https://www.skool.com/become-ai-researcher-2669/about
DeepSeek Sparse Attention - https://youtu.be/kAEPS_AUGy8
Discord (Open Superintelligence Lab) - https://discord.gg/6AbXGpKTwN
Novita is giving 50% OFF on GPUs (4090, 5090, H100, B200…), juse select *spot billing*. If you use our affiliate link, Novita will gift compute to our open-source AI project ❤️ - https://novita.ai/?ref=mjqyndm&utm_source=affiliate
X - https://x.com/VukRosic99
0:00 - Long Context Idea
1:57 - Deepseek OCR
2:36 - Encoder Issues
3:20 - Encoder Architecture
4:33 - Local Attention
7:12 - CNN Compressor
9:17 - Vision Transformer
10:59 - LLM Decoder
11:45 - Final Thoughts
