cyrilzakka

NameDrop

Poor man's replica of iOS 17 NameDrop animation

MAE3D

Masked Auto-Encoding for Large Scale Pretraining of Video Data

llm-playbook

Research Notes on Large Language Models

Chat

A SwiftUI Chat UI framework with fully customizable message cells and a built-in media picker

chat-ui

Open source codebase powering the HuggingChat app

SlidingRuler

A sliding ruler control for SwiftUI - fixing

2023-PAWS-Dashboard

PAWS Clinical Dashboard

dolma

Data and tools for generating and inspecting OLMo pre-training data.

flux

Official inference repo for FLUX.1 models

gazelle

Joint speech-language model - respond directly to audio!

llama.cpp

Port of Facebook's LLaMA model in C/C++

LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.

llmfarm_core.swift

Swift library to work with llama and other large language models.

macOS-Icons

Replacement app and document icons for macOS

minbpe

Minimal, clean, educational code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

mistral-mlx

MLX implementation of the Mistral 7B model

ml-aim

This repository provides the code and model checkpoints of the research paper: Scalable Pre-training of Large Autoregressive Image Models

mlx

MLX: An array framework for Apple silicon

OLMo

Modeling, training, eval, and inference code for OLMo

open_clip

An open source implementation of CLIP.

orbit-surgical

parler-tts

Inference and training library for high-quality TTS models.

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

SwiftUI-Explorations

mono repo for all my SwiftUI explorations ✨

text-generation-inference

Large Language Model Text Generation Inference

train-with-fsdp

TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Volume-Rendering-In-iOS

Implement Volume Rendering in iOS development environment