AI & ML
Transformers & LLMs
Transformers changed everything. Master the architecture that powers modern AI.
The Attention Mechanism
Self-Attention Explained
Multi-Head Attention
Positional Encoding
Transformer Architecture
Encoder Architecture
Decoder Architecture
Encoder-Decoder vs Decoder-Only
Large Language Models
Scaling Laws and Emergence
Tokenization Deep Dive
In-Context Learning
Modern LLM Variants
GPT Family Architecture
Open-Source LLMs
Mixture of Experts
Vision Transformers (ViT)