DeepSeek-V3
25:36
DeepSeek R1 Theory Overview | GRPO + RL + SFT
57:45
Visualizing transformers and attention | Talk for TNG Big Tech Day '24
14:21
Building a fully local "deep researcher" with DeepSeek-R1
24:01
ChatGPT is made from 100 million of these [The Perceptron]
24:06
WHY R1 & o1 Models Underthink Complex Reasoning (+ Solution)
1:09:00
[GRPO Explained] DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
19:44
A Visual Guide to Mixture of Experts (MoE) in LLMs
27:14