PhyseaWiki How AI actually works Papers physea.ai →

Subject 02 · Builds on Foundations

Language Model Architecture

How a language model is built: the transformer, attention, embeddings, context windows, and how text is generated one token at a time.

26 pages across 6 topics

The transformer

The architecture behind modern LLMs.

Attention

How tokens look at each other.

Embeddings & vectors

Meaning as geometry.

Context windows

How much a model can hold at once.

Parameters & layers

What a model is made of, and how big.

How text is generated

Sampling the next token.