Lee Drake

bruker-xrf-ppm-plot. Jupyter notebook pulls data from results.csv, cleans, and displays in a biplot

academic-research-skills. Academic Research Skills for Claude Code: research → write → review → revise → finalize

llm_aided_ocr. Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs

R-workflow-for-shape-analysis-using-MoE. Automated R pipeline for unsupervised outline classification, designed for cross-cultural archaeological studies. The code supports the presentation of the same title at CAA 2026 conference.

oracc-parser. A package for easily parsing and exporting oracc jsons for downstream usages.

ProtoSnap. Python

codex. Lightweight coding agent that runs in your terminal

gpu-auto-shutdown. Shell

kvpress. LLM KV cache compression made easy

pytorch-frame. Tabular Deep Learning Library for PyTorch

hnet. H-Net: Hierarchical Network with Dynamic Chunking

potnia. Potnia is an open-source Python library designed to convert Romanized transliterations of ancient texts into Unicode representations of their respective native scripts.

SumTablets. SumTablets is a dataset designed for training Sumerian transliteration models.

PregnancyMillions. Data and analyses for the paper "Pregnancy and postpartum dynamics revealed by millions of lab tests"

DeepGEMM. DeepGEMM: clean and efficient BLAS kernel library on GPU

TransformerEngine. A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

oracc. All the sources and documentation for Oracc

itihasa. A large scale Sanskrit-English translation dataset

Ancient-Language-Decipherer. Creating a model for the recognition and classification of ancient Egyptian Hieroglyphs. Using transfer learning on convolutional neural networks created with TensorFlow 2.0

the_well. A 15TB Collection of Physics Simulation Datasets

paleo_sea_level. Global Archive of Paleo Sea Level Indicators and Proxies (GAPSLIP)

gpu_poor. Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

us-potus-model. Code for a dynamic multilevel Bayesian model to predict US presidential elections. Written in R and Stan.

FruitNeRF. [IROS24] Offical Code for "FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework" - Inegrated into Nerfstudio

cminpack. A C/C++ rewrite of the MINPACK software (originally in FORTRAN) for solving nonlinear equations and nonlinear least squares problems

data. This is a copy of the daily dump of catalogue and ATF data from the Cuneiform Digital Library Initiative (http://cdli.ucla.edu)

multilingual-t5. Python

araT5. AraT5: Text-to-Text Transformers for Arabic Language Understanding

ChebyKAN. Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.

MLP-KAN. Kolmogorov–Arnold Networks with modified activation (using MLP to represent the activation)

MunichProcedure. R-Script of the Munich Procedure to develop coefficient corrections by linear regressions applied on p-XRF data

ThaumatoAnakalyptor. Automatic Scroll Segmentation Pipline for CT Scans of Herculaneum papyri

megablocks-public.

CenoCO2. Code and data for Cenozoic CO2 reconstruction

assemblyphysics. Mathematica

fine-tune-mistral. Fine-tune mistral-7B on 3090s, a100s, h100s

lipdR. lipdR package development repository

SHAPforxgboost. SHAP (SHapley Additive exPlnation) visualization for 'XGBoost' in 'R'

llama.cpp. LLM inference in C/C++

textgen. Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

PlantVillage-Dataset. Dataset of diseased plant leaf images and corresponding labels

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

fah-client-bastet. Folding@home client, code named Bastet

eps. Evolution of planetary systems

asteroids_atlas_of_space. Code, data, and instructions for mapping orbits of asteroids in the solar system

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

tft_tf2. Temporal Fusion Transformers for Tensorflow 2.x

ha-sensor.owlet. Owlet Smart Sock v2/v3 Sensor Integration for HomeAssistant using the modern Owlet API.

uawardata. The data behind uawardata.com

oryx_data. This is a repo for the data scraped using the scrape_oryx.R program. Updated daily at 22:30 EDT/EST

CovidColoradoCharts. Charts from Colorado's COVID data

scrape_oryx. A simple R script for extracting tabular data from Oryx' excellent post detailing materiel lost by all sides in the [Russian invasion of Ukraine](https://www.oryxspioenkop.com/2022/02/attack-on-europe-documenting-equipment.html).

uts. Unevenly Spaced Time Series in R

traces. A Python library for unevenly-spaced time series analysis

covid-19-excess-deaths-tracker. Source code and data for The Economist's covid-19 excess deaths tracker

xrftools. XRF tools for R

mtcnn. MTCNN face detection implementation for TensorFlow, as a PIP package.

tensorflow_macos. TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.

jukebox. Code for the paper "Jukebox: A Generative Model for Music"

simplerspec. Streamlining data processing and modeling for spectroscopy applications

awesome-deep-learning-papers. The most cited deep learning papers

covid-county-app. A simple Shiny app for tracking COVID19 cases in your county

shap. A game theoretic approach to explain the output of any machine learning model.

covid19. Analyses about the COVID-19 virus

ncov-cfr. R code and documentation to estimate case fatality ratio of COVID-19 from cases outside China

xgboost. Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow

bayesian-neural-network-blogpost. Building a Bayesian deep learning classifier

homebrew-r-srf. Custom Homebrew R formula with tcl-tk support and additional options

cell_counting_v2. Python

tidytuesday. Official repo for the #tidytuesday project

DABEST-python. Data Analysis with Bootstrapped ESTimation

tpu. Reference models and tools for Cloud TPUs.

bartMachine. An R-Java Bayesian Additive Regression Trees implementation

tensorflow-build-archived. TensorFlow binaries supporting AVX, FMA, SSE

tensorflow. An Open Source Machine Learning Framework for Everyone

NLP-with-Python. Scikit-Learn, NLTK, Spacy, Gensim, Textblob and more

plaidml. PlaidML is a framework for making deep learning work everywhere.

mclapply-memory. Why does mclapply take so much memory?

feature-selector. Feature selector is a tool for dimensionality reduction of machine learning datasets

shiny. Easy interactive web applications with R

caret. caret (Classification And Regression Training) R package that contains misc functions for training and plotting classification and regression models

ggplot2. An implementation of the Grammar of Graphics in R

water-tools. John Fleck's water tools

geos-chem. GEOS-Chem "Science Codebase" repository. Contains GEOS-Chem science routines, run directory generation scripts, and interface code. This repository is used as a submodule within the GCClassic and GCHP wrappers, as well as in other modeling contexts (external ESMs).

neural-enhance. Super Resolution for images using deep learning.

tweetbotornot. 🤖 R package for detecting Twitter bots via machine learning

bcp. :exclamation: This is a read-only mirror of the CRAN R package repository. bcp — Bayesian Analysis of Change Point Problems. Homepage: https://github.com/zhaokg/bcp Report bugs for this package: https://github.com/zhaokg/bcp/issues

datakit-project. Project generator for use with the datakit framework.