Decoder-Only

A transformer architecture that uses only the decoder stack with causal masking, treating every task as next-token prediction on a single concatenated sequence.

LLMs

BACKLOG · WORK IN PROGRESS

This term is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.

Back to wiki Track progress on GitHub