msapaydin

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

cosmopolitan

build-once run-anywhere c library

llamafile

Distribute and run LLMs with a single file.

practical-python

Practical Python Programming (course by @dabeaz)

sktime

A unified framework for machine learning with time series

handson-ml3

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

yosys

Yosys Open SYnthesis Suite

ostep-code

Code from various chapters in OSTEP (http://www.ostep.org)

AdaBound

An optimizer that trains as fast as Adam and as good as SGD.

category_encoders

A library of sklearn compatible categorical variable encoders

ostep-homework

cs228-notes

Course notes for CS228: Probabilistic Graphical Models.

cortex

Drop-in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM, ONNX). Powers 👋 Jan

hls4ml

Machine learning on FPGAs using HLS

zemberek-nlp

NLP tools for Turkish.

pcc_3e

Online resources for Python Crash Course, 3rd edition, from No Starch Press.

Merlin

NVIDIA Merlin is an open source library providing end-to-end GPU-accelerated recommender systems, from feature engineering and preprocessing to training deep learning models and running inference in production.

emacs-copilot

Large language model code completion for Emacs

hover_net

Simultaneous Nuclear Instance Segmentation and Classification in H&E Histology Images.

dcai-lab

Lab assignments for Introduction to Data-Centric AI, MIT IAP 2024 👩🏽‍💻

IntroToPython

Files associated with our book Intro to Python for Computer Science and Data Science

GlistEngine

GlistEngine is a cross platform OpenGL game engine written in C++

protein-sequence-embedding-iclr2019

Source code for "Learning protein sequence embeddings using information from structure" - ICLR 2019

plip

Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.

medperf

An open benchmarking platform for medical artificial intelligence using Federated Evaluation.

prose

Multi-task and masked language model-based protein sequence embedding models.

whole-slide-cnn

This repository provides scripts to reproduce the results in the paper "An annotation-free whole-slide training approach to pathological classification of lung cancer types by deep learning".

finn-base

Open Source Compiler Framework using ONNX as Frontend and IR

datastructures-visualization

Visualization of data structures and algorithms using Python and Tkinter