mzguntalan/zephyr

Zephyr is a declarative neural network library on top of JAX allowing for easy and fast neural network designing, creation, and manipulation

28
/ 100
Experimental

This library helps machine learning engineers and researchers design and build neural networks quickly and efficiently using JAX. It takes a function describing the network's structure and automatically handles the complex parameter initialization, outputting a ready-to-use, JAX-compatible neural network function. This is ideal for those who prefer a purely functional approach to deep learning model development.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher who works with JAX and wants to define neural networks as simple functions, minimizing boilerplate code and focusing on the network's mathematical structure.

Not ideal if you are accustomed to object-oriented neural network frameworks (like PyTorch or TensorFlow Keras) or if you are not already working within the JAX ecosystem.

deep-learning-engineering neural-network-design machine-learning-research functional-programming-ML JAX-model-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

36

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Sep 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mzguntalan/zephyr"

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