rasbt

LLMs-from-scratch

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

ml-engineering

Machine Learning Engineering Open Book

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

litgpt

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

marimo

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

courses

This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)

phoenix

AI Observability & Evaluation

lectures

Material for cuda-mode lectures

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

pytorch_tabular

A standard framework for modelling Deep Learning Models for tabular data

hlb-CIFAR10

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

lightning-thunder

Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.

nbQA

Run ruff, isort, pyupgrade, mypy, pylint, flake8, and more on Jupyter Notebooks

nanoT5

Fast & Simple repository for pre-training and fine-tuning T5-style models

a-PyTorch-Tutorial-to-Super-Resolution

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution

LLaMA-Cult-and-More

Large Language Models for All, 🦙 Cult and More, Stay in touch !

SRGAN-PyTorch

A simple and complete implementation of super-resolution paper.

hopular

Hopular: Modern Hopfield Networks for Tabular Data

sheeprl

Distributed Reinforcement Learning accelerated by Lightning Fabric

dora

Implementation of DoRA

litdata

Transform datasets at scale. Optimize datasets for fast AI model training.

cookie

Scientific Python Library Development Guide and Cookiecutter

mint

MinT: Minimal Transformer Library and Tutorials

neurips_llm_efficiency_challenge

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

TabularBenchmarks

jekyll-anchor-headings

A GitHub Pages compatible way of adding anchors to your headings without a plug-in or JavaScript :octocat:

graphml-class

Full Stack Graph Machine Learning: Theory, Practice, Tools and Techniques

Training-Studio_app

Lightning HPO & Training Studio App

bskycheck