pkulium

notes

Robustness-Aware-Pruning-ADMM

Code release for "Adversarial Robustness vs Model Compression, or Both?"

sparsegpt_admm

Code for the ICML 2023 paper "SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot".

admm_lora

amc

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

ANP_backdoor

Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

modelpruning-devNxM

BetterChatGPT

An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)

Black-Box-Defense-Linear

Robustify Black-Box Models (ICLR'22 - Spotlight)

BlackBox

client_defense

Github Repo for AAAI 2023 paper: On the Vulnerability of Backdoor Defenses for Federated Learning

DBA

DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)

Defending-Against-Backdoors-with-Robust-Learning-Rate

The code of AAAI-21 paper titled "Defending against Backdoors in Federated Learning with Robust Learning Rate".

HIER

HierSafeFL

I-BAU

Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''

layer-adaptive-sparsity

In progress.

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

Mezo_NM

Muwa-OPT

A budget-friendly OPT-based LLM

NMFADMM

A sparsity aware implementation of "Alternating Direction Method of Multipliers for Non-Negative Matrix Factorization with the Beta-Divergence" (ICASSP 2014).

PNP_BlackBox

ProbMask-official

Implementation of Effective Sparsification of Neural Networks with Global Sparsity Constraint

PyTorch-CIFAR-10-autoencoder

This is a reimplementation of the blog post "Building Autoencoders in Keras". Instead of using MNIST, this project uses CIFAR10.

QMeZO

MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

RNP

Reconstructive Neuron Pruning for Backdoor Defense (ICML 2023)

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

VRPGE-Sparse-Training

Implementation of Efficient Neural Network Training via Forward and Backward Propagation Sparsification

wanda

A simple and effective LLM pruning approach.