Transformer Systems · Skill Path
Attention From Scratch
A focused transformer path for implementing attention scores, self-attention, masks, and multi-head shape transforms.
Transformer Systems 4 steps intermediate to advanced 7.2 hr 1 review decks
- 01 Attention Mechanism Lesson · Foundations And Data Flow · 1.5 hr · Reading
- 02 Self-Attention Mechanics Lesson · Attention And Positional Information · 2.5 hr · Reading
- 03 Padding, Causal, And Packed Masks Lesson · Attention And Positional Information · 1.7 hr · Review deckFlashcard deck
- 04 Multi-Head Self-Attention Lesson · Attention And Positional Information · 1.5 hr · Reading