Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.

build-once run-anywhere c library

An operating system in your terminal

Real-time webcam demo with SmolVLM and llama.cpp server

◉ Universal Intelligence: AI made simple.

OSX hfjobs menubar app

Thin wrapper around GGML to make life easier

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

The ultimate training toolkit for finetuning diffusion models

A curated list of resources about AI agents for Computer Use, including research papers, projects, frameworks, and tools.

🤖 Just a command runner

Wrapping C `tokenizers` in ergonomic, safe Swift.

Tools for merging pretrained large language models.

Minimal implementation of a Byte Pair Encoding (BPE) tokenizer in Zig

https://hf.co/hexgrad/Kokoro-82M

Fast ML inference & training for ONNX models in Rust

Moved to Codeberg

A cat(1) clone with wings.

Tracking the evolution of Artificial Intelligence

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Notebooks for fine tuning pali gemma

Open source health metric tracking.

Interface for OuteTTS models.

🎤⌨️ Acoustic keyboard eavesdropping

Notebook and Scripts that showcase running quantized diffusion models on consumer GPUs

Profile your CoreML models directly from Python 🐍

cli tool to deploy TGI via nixos on aws

FFmpeg for browser, powered by WebAssembly

Safe rust wrapper around CUDA toolkit

Transformers PHP is a toolkit for PHP developers to add machine learning magic to their projects easily.