Skip to main content
⌘K
Drop a repoSign up
REPOLum1104/Understand-Anything+606 stars 24hREPOanthropics/financial-services-plugins+396 stars 24hREPOrohitg00/ai-engineering-from-scratch+331 stars 24hREPOaddyosmani/agent-skills+327 stars 24hREPOcolbymchenry/codegraph+327 stars 24hREPOLum1104/Understand-Anything+606 stars 24hREPOanthropics/financial-services-plugins+396 stars 24hREPOrohitg00/ai-engineering-from-scratch+331 stars 24hREPOaddyosmani/agent-skills+327 stars 24hREPOcolbymchenry/codegraph+327 stars 24h
Glossary

What is transformer?

A transformer is the neural-network architecture behind modern language models, using self-attention to weigh how every token in the input relates to every other.

The transformer replaced recurrent networks by processing a whole sequence in parallel and letting each token attend to all others through self-attention. That design scales efficiently on modern hardware and underlies essentially every current large language model.

Open-source implementations of the architecture — and the model weights built on it — let teams study, run, and adapt transformers directly rather than only through a hosted API.

Best open-source LLMs →

Trending transformer projects

  1. NVlabs/Sana

    SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

    ★ 7.6K+92 · 24hmomentum 11Python

  2. kyegomez/OpenMythos

    A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

    ★ 13.4K+18 · 24hmomentum 9Python

▌ transformer — FAQ

What is transformer?
A transformer is the neural-network architecture behind modern language models, using self-attention to weigh how every token in the input relates to every other. The transformer replaced recurrent networks by processing a whole sequence in parallel and letting each token attend to all others through self-attention. That design scales efficiently on modern hardware and underlies essentially every current large language model.