harveyp123

LinGCN-Neurips23

Official Implementation of "LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference"

MaxK-GNN

AutoReP

Automatic ReLU Reduction

ICCD_SpTrn_SLR

Comparison between sparse training and SLR method on GNN dataset

PASNet-DAC2023

Official Implementation of DAC 2023 paper: PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network Deployment

DGL-clustering-GPU-Nvidia

An example for DGL cluster/subgraph manipulation

MNIST-Training

Minimum example for mnist training

Pytorch-DDP-Example

A minimum example for pytorch DDP based single node multi-GPU training on MNIST dataset, with different gradient compression

a-PyTorch-Tutorial-to-Object-Detection

SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection

chatgpt-retrieval

cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

harveyp123.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

LLM-scientific-feedback

Can large language models provide useful feedback on research papers? A large-scale empirical analysis.

Nvidia-GPU-Performance-Benchmark

Performance Benchmark on different data types

PaLM-rlhf-pytorch

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

sparsegpt

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

mypy

Optional static typing for Python

StackOverflow

https://blog.pother.ca/StackOverflow/ Code and Examples to accompany my answers and questions on the StackOverflow website.

Conditional_Diffusion_MNIST

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

eval

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

ICLR2023-OpenReviewData

ICLR 2023 Paper submission analysis from https://openreview.net/group?id=ICLR.cc/2023/Conference

lm-evaluation-harness

Masked_Autoencoders

PyTorch implementation of Masked Autoencoders

memit

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

scattermoe

setup_imagenet

template1

Train-BERT-for-Masked-Language-Modeling-Tasks

GitHub repo for TDS article "How to Train BERT for Masked Language Modeling Tasks"