Core examples#
Core examples are hosted on the GitHub Flax repository in the examples directory.
Each example is designed to be self-contained and easily forkable, while reproducing relevant results in different areas of machine learning.
Some of the examples below have a link “Interactive🕹” that lets you run them directly in Colab.
Transformers#
Gemma : A family of open-weights Large Language Model (LLM) by Google DeepMind, based on Gemini research and technology.
LM1B : Transformer encoder trained on the One Billion Word Benchmark.
- Diffusion Models :
A simple example of an image diffusion model using a U-Net architecture.
Toy examples#
NNX toy examples directory contains a few smaller, standalone toy examples for simple training scenarios.