Completed
Transformer LM Component 2: Self-Attention
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
The Narrated Transformer Language Model
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 The Architecture of the Transformer
- 3 Model Training
- 4 Transformer LM Component 1: FFNN
- 5 Transformer LM Component 2: Self-Attention
- 6 Tokenization: Words to Token Ids
- 7 Embedding: Breathe meaning into tokens
- 8 Projecting the Output: Turning Computation into Language
- 9 Final Note: Visualizing Probabilities