Radar ·
Peter Bloem's tutorial: transformers from scratch
A blog post by Peter Bloem that explains the internal components of the transformer from basic principles, focusing on attention. Shared as study material on the architecture.
Radar records the post Transformers from Scratch, by Peter Bloem, dated 12 November 2026 in the bookmark record. The text presents itself as a self-contained explanation of the transformer architecture: it describes its internal components and aims to make the attention mechanism understandable from basic principles. The source is a blog post shared as study material; the record contains no benchmark data, experimental results or product claims.
To consult the original, find the post by its title and the author's name through a search engine or the author's blog archive, and check the publication date and text version before citing it. Anyone using AI to study this topic should avoid pasting personal data, credentials or internal organizational documents into any model; prefer fictional examples and check generated explanations against the primary source, since a model can get mathematical details wrong.
Original source: Transformers from Scratch: tutorial de Peter Bloem