jpata

SegmentAnythingMobile

omnijet_alpha

Code of the paper "OmniJet-α: The first cross-task foundation model for particle physics" (https://arxiv.org/abs/2403.05618).

PlotNeuralNet

Latex code for making neural networks diagrams

MLCourse_2023

HEPT

[ICML'24 Oral] LSH-Based Efficient Point Transformer (HEPT)

ml-engineering

Machine Learning Engineering Open Book

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

JetReconstruction.jl

Jet reconstruction (reclustering) with Julia

antikt-python

Implementation of the AntiKt jet finding algorithm in Python

flash-attention

Fast and memory-efficient exact attention

flatformer

[CVPR'23] FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

hls4ml-tutorial

Tutorial notebooks for hls4ml

HGQ

High Granularity Quantizarion for Ultra-Fast Machine Learning Applications on FPGAs

Muons-Data-Generation

To go along with https://github.com/jedlimlx/Computed-Tomography-AI

Muon-Tomography-AI

$\mu$-Net: ConvNeXt-Based U-Nets for Muon Tomography

LLMFarm

llama and other large language models on iOS and MacOS offline using GGML library.

ml-stable-diffusion

Stable Diffusion with Core ML on Apple Silicon

diffusionbee-stable-diffusion-ui

Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.

stable-diffusion.cpp

Stable Diffusion in pure C/C++

course

Main course repo for IAP 2022

DiffusionMBIR

Official PyTorch implementation of the CVPR 2023 paper "Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models (https://arxiv.org/abs/2211.10655)"

hg-tspn-pflow

UltraDark.jl

Simulations of cosmological scalar fields

llama.cpp

LLM inference in C/C++

whisper.cpp

Port of OpenAI's Whisper model in C/C++

wrapyfi-examples_llama

Inference code for facebook LLaMA models with Wrapyfi support

STEGO

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Grokking-Deep-Learning

this repository accompanies the book "Grokking Deep Learning"

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

cookiecutter4fair

A logical, standardized, but flexible project structure for sharing AI and data science work following FAIR principles.