Matthew Kehoe's Projects
Work on ML for 100+ Days Straight
π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
An annotated implementation of the Transformer paper.
The PyTorch-based audio source separation toolkit for researchers
A curated list of data science & AI guided projects to start building your portfolio
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Awesome-LLM: a curated list of Large Language Model
A topic-centric list of HQ open datasets.
Notes and links from the book club meetings
Chebfun: numerical computing with functions.
A collection of Jupyter Notebooks highlighting data science and machine learning projects.
Cheat Sheets
Curated list of data science interview questions and answers
π€ The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
A MNIST-like fashion product database. Benchmark :point_down:
The open-source tool for building high-quality datasets and computer vision models
A very simple framework for state-of-the-art Natural Language Processing (NLP)
The textbook Computational and Inferential Thinking: The Foundations of Data Science
Fundamentals of Numerical Computing in Julia
Generative Pre-Trained Physics-Informed Neural Networks Implementation
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
A HighβOrder Perturbation of Surfaces/Asymptotic Waveform Evaluation (HOPS/AWE) algorithm for Grating Scattering Problems.
HydraViT is a PyTorch implementation of the HydraViT model, an adaptive multi-branch transformer for multi-label disease classification from chest X-ray images. The repository provides the necessary code to train and evaluate the HydraViT model on the NIH Chest X-ray dataset.
Google Colab notebooks for the Intro to Python class
The Iris Dataset contains four features (length and width of sepals and petals) of 50 samples of three species of Iris (Iris setosa, Iris virginica and Iris versicolor). These measures were used to create a linear discriminant model to classify the species.
IrisME is a fast and accurate software for calculating scattering coefficients in gratings of holes perforating a metallic film. IrisME is based on the Modal Expansion of the electromagnetic fields. The method was initially developed to investigate the phenomenom of Extraordinary Optical Transmission.
This repo contains the code to forecast EUV irradiance 'Stan' bands from solar images up to six days in advance.
Various Java programs for data and numerical analysis including an arbitrary precision complex number library.
Book on Julia for Data Science