Flax

Vision TransformerJupyter Notebook

Official JAX/Flax implementation of Vision Transformer (ViT) and MLP-Mixer for image recognition, with pre-trained models.

Flax EngineC++

A high-quality modern 3D game engine written in C++ and C# with a focus on fast workflow and stunning graphics.

ScenicPython

A JAX library for rapid prototyping of large-scale attention-based vision models across images, video, audio, and multimodal data.

EasyLMPython

A JAX/Flax-based framework for easy and scalable pre-training, fine-tuning, evaluation, and serving of large language models.