M.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any Spotify song, adjusts system and Spotify volume, performs calculations, browses the web and internet, se…

Benchmarking and Testing FastKAN

Llama3.1 x Kolmogorov–Arnold Networks

KAN (Kolmogorov–Arnold Networks) in the MLX framework

Utilities intended for use with Llama models.

Stable Diffusion with Core ML on Apple Silicon

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Fast and memory-efficient exact attention

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

An esolang in TypeScript, for heaven's sake.

Deep learning library implemented from scratch in numpy. Mixtral, Mamba, LLaMA, GPT, ResNet, and other experiments.

Simple artificial neural network implemented in C#

LLM based agents with proactive interactions, long-term memory, external tool integration, and local deployment capabilities.

Fast parallel LLM inference for MLX

Tool to download models from Huggingface Hub and convert them to GGML/GGUF for llama.cpp

Faster Whisper transcription with CTranslate2

MARS5 speech model (TTS) from CAMB.AI

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Converts text to speech in realtime

4M: Massively Multimodal Masked Modeling

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

LLM101n: Let's build a Storyteller

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

The official Meta Llama 3 GitHub site

Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

The official implementation of ImageBind-LLM and Whisper-LLM from the paper "Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech".

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Implementation of Diffusion Transformer Model in Pytorch

High-quality datasets, tools, and concepts for LLM fine-tuning.