pbloem/former

Simple transformer implementation from scratch in pytorch. (archival, latest version on codeberg)

49
/ 100
Emerging

This project is an archived, basic implementation of a transformer neural network, useful for understanding the foundational architecture. It takes in sequential data, such as text, and processes it to produce another sequence or a representation, demonstrating how transformer models learn relationships within data. It's intended for students or researchers who want to delve into the core mechanics of transformer models from a computational perspective.

1,092 stars. No commits in the last 6 months.

Use this if you are a student or researcher wanting to learn the fundamental, low-level implementation of a transformer architecture from scratch.

Not ideal if you need a production-ready, high-performance, or actively maintained transformer library for real-world applications.

neural-networks deep-learning-education natural-language-processing-research machine-learning-fundamentals
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

1,092

Forks

172

Language

Python

License

MIT

Last pushed

Mar 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pbloem/former"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.