Inference code for Mistral and Mixtral hacked up into original Llama implementation

The single instruction C compiler

A library for encoding and decoding web audio as OggOpus.

Inference Llama 2 in one file of pure Python

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

JavaScript 3D library.

MOZ_text glTF Extension

A vuejs application which allow users to play piano with friends!