A step-by-step breakdown of the transformer architecture, now used widely for natural language processing in models such as ChatGPT.
Feel free to like, subscribe and leave a comment if you find this helpful!
CHAPTERS
--------------------
Introduction 00:00
High-level overview 01:57
Architecture 06:10
Word vectorization 07:00
Positional encoding 10:25
Encoder 13:00
Decoder 21:17
Word selection 24:45
Limitations 25:52