Transformers explained REMASTERED | The architecture behind LLMs

All you need to know about the transformer architecture: How to structure the inputs, attention (Queries, Keys, Values), positional embeddings, residual connections. Bonus: an overview of the difference between Recurrent Neural Networks (RNNs) and transformers.

Outline:
00:00 Transformers explained
00:47 Text inputs
02:29 Image inputs
03:57 Next word prediction / Classification
06:08 The transformer layer: 1. MLP sublayer
06:47 2. Attention explained
07:57 Attention vs. self-attention
08:35 Queries, Keys, Values
11:26 Multi-head attention
13:04 Attention scales quadratically
13:53 Positional embeddings …

architecture attention bonus classification difference embeddings explained image inputs keys llms networks neural networks next overview prediction recurrent neural networks residual text transformer transformer architecture transformers values word