How LLMs Work

A comprehensive course on Large Language Models. From tokenization to reinforcement learning, understand the technology powering ChatGPT, Claude, and beyond.

8 Modules covering the full stack 3.5 hours of source material Free and open source
100K
Tokens in GPT-4 vocabulary
405B
Parameters in Llama 3.1
15T
Training tokens (modern LLMs)
$672
To reproduce GPT-2 today

Course Modules

01

Pre-Training Fundamentals

45 min
→ 02

Inference & Base Models

30 min
→ 03

Post-Training & Fine-Tuning

45 min
→ 04

Hallucinations & Mitigations

30 min
→ 05

Reinforcement Learning

45 min
→ 06

Future Directions

15 min
→ 07

AI Analytics Platforms

Bonus
→ 08

Memory Systems for LLMs

Bonus
→