A Plasma Toroid Project. Powered by Diagon Alley Magic Shop.

LLM training in simple, raw C/CUDA

Inference Llama 2 in one file of pure C

DSPy: The framework for programming—not prompting—language models

We have made you a wrapper you can't refuse

🙌 OpenHands: Code Less, Make More

High-Resolution Image Synthesis with Latent Diffusion Models

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

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 80% less memory

🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).

A nearly-live implementation of OpenAI's Whisper.

SunPy - Python for Solar Physics

Kolmogorov Arnold Networks

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU su…

Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.

ImageBind One Embedding Space to Bind Them All

structured outputs for llms

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Set up a modern web app by running one command.

VectorHub is a free, open-source learning website for people (software developers to senior ML architects) interested in adding vector retrieval to their ML stack.

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

The Memory layer for your AI apps

Examples in the MLX framework

Superfast AI decision making and intelligent processing of multi-modal data.

ChatGPT Telegram Bot running in AWS Lambda

A Github Action to deploy AWS Lambda functions written in Python with their dependencies in a separate layer.