Index - Modern LLMs

Skip to Content

FOUNDATIONS
Chapter 1: Neural networks
Chapter 2: Language modeling
Chapter 3: The transformer
MODEL ARCHITECTURE
Chapter 4: Scaling
Chapter 5: Modern variants
Chapter 6: Interpretability
TRAINING
Chapter 7: Pre-training
Chapter 8: Post-training
Chapter 9: Evaluation
INFERENCE
Chapter 10: Hardware
Chapter 11: Serving
Chapter 12: Sampling & beyond

FOUNDATIONS
Chapter 1: Neural networks
Chapter 2: Language modeling
Chapter 3: The transformer
MODEL ARCHITECTURE
Chapter 4: Scaling
Chapter 5: Modern variants
Chapter 6: Interpretability
TRAINING
Chapter 7: Pre-training
Chapter 8: Post-training
Chapter 9: Evaluation
INFERENCE
Chapter 10: Hardware
Chapter 11: Serving
Chapter 12: Sampling & beyond

Questions? Leave me feedback Opinions? Suggest an edit

This site is a 12-chapter, front-to-back-readable guide on how modern large language models work, for experienced engineers.

Chapter 1: Neural networks

Chapter 2: Language modeling