DEVICE/BROWSER INFO
aatventure
How GPT and other large language models (LLMs) work. Transformers deep dive.
00:00 - Intro
00:33 - The transformer model
01:30 - Predicting the next word
02:30 - Tokenization
05:06 - Representing meaning
07:17 - Positional encoding
09:17 - Attention head
14:49 - Genspark
16:35 - Multiple heads
19:30 - Add and norm
21:45 - Feed forward neural net
24:08 - Multiple decoder blocks
24:50 - Final layer
27:03 - Training the model