Experiments with local as well as models available through an api
GGUF implementation in C as a library and a tools CLI program
Create your own AI by fine-tuning open source models
This is our own implementation of 'Layer Selective Rank Reduction'
First token cutoff sampling inference example
MLX: An array framework for Apple silicon
Benchmark of Apple's MLX operations on mlx gpu, cpu, torch mps and cuda.
Scripts to create your own moe models using mlx
Port of Andrej Karpathy's nanoGPT to Apple MLX framework.
ChatGPT-Style Web UI Client for Ollama 🦙
Modeling, training, eval, and inference code for OLMo
Build AI Assistants using function calling
From anywhere you can type, query and stream the output of an LLM or any other script
A reinforcement learning framework based on MLX.
Integrate cutting-edge LLM technology quickly and easily into your apps
Hackable and optimized Transformers building blocks, supporting a composable construction.