🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Quick exploration into fine tuning florence 2

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capa…

Fast parallel LLM inference for MLX

LLM101n: Let's build a Storyteller

Implementation of nougat that focuses on processing pdf locally.

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

Your image is almost there!

Phi-3 for Mac: Locally-run Vision and Language Models for Apple Silicon

Blue-text Bot AI. Uses Ollama + AppleScript

Swift Package to implement a transformers-like API in Swift

A library for mechanistic interpretability of GPT-style language models

Implementation of Nougat Neural Optical Understanding for Academic Documents

High-performance In-browser LLM Inference Engine

Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.

Turn any webpage into structured data using LLMs

A prototype of a tool that generates web forms from document forms

LLM training in simple, raw C/CUDA

structured outputs for llms

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

Zero-Shot Speech Editing and Text-to-Speech in the Wild

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Explore a simple example of utilizing MLX for RAG application running locally on your Apple Silicon device.

A framework for Claude Opus to intelligently orchestrate subagents.

Automate the analysis of GitHub repositories for LLMs with RepoToTextForLLMs. Fetch READMEs, structure, and non-binary files efficiently. Outputs include analysis prompts to aid in comprehensive re…

ChatMLX is a large model real-time conversation app implemented using MLX.🚧

A simple script to enhance text editing across your Mac, leveraging the power of MLX. Designed for seamless integration, it offers real-time text correction everywhere you type.