iamgroot42

mlx

MLX: An array framework for Apple silicon

pykan

Kolmogorov Arnold Networks

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

LaVague

Large Action Model framework to develop AI Web Agents

pytorch-cifar100

Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)

adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks]

executorch

On-device AI across mobile, embedded and edge for PyTorch

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

tensordict

TensorDict is a pytorch dedicated tensor container.

pydoc-markdown

Create Python API documentation in Markdown format.

JailbreakingLLMs

persuasive_jailbreaker

Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!

advprompter

Official implementation of AdvPrompter https//arxiv.org/abs/2404.16873

TAP

TAP: An automated jailbreaking method for black-box LLMs

torch-influence

A simple PyTorch implementation of influence functions.

logix

AI Logging for Interpretability and Explainability🔬

EfficientNetV2-pytorch

EfficientNetV2 pytorch (pytorch lightning) implementation with pretrained model

torch-warmup-lr

Warmup learning rate wrapper for Pytorch Scheduler

sgd-sparse-features

SGD with large step sizes learns sparse features [ICML 2023]

code-autodan

An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)

mink-plus-plus

Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936

pubstats

Leveraging-Adversarial-Examples-to-Quantify-Membership-Information-Leakage

M-FAC

Efficient reference implementations of the static & dynamic M-FAC algorithms (for pruning and optimization)

gaussian_mip

Gaussian Membership Inference Privacy (NeurIPS 2023)

bench_hvp

parameters_or_privacy

uva-seas-thesis-template

Thesis/Dissertation template for School of Engineering and Applied Science, University of Virginia

SuperDeepFool

Official version of the PyTorch implementation of SuperDeepFool adversarial attack.

SeriesOfHessianVectorProducts

This repository contains code for the paper Series of Hessian-Vector Products for Saddle-Free Newton Optimisation of Neural Networks, submitted to TMLR.