HeywardLiu

algorithm-exercise

Data Structure and Algorithm notes. 数据结构与算法/leetcode/lintcode题解/

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

tensordict

TensorDict is a pytorch dedicated tensor container.

tiny-gpu

A minimal GPU design in Verilog to learn how GPUs work from the ground up

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT better.

awesome-chatgpt-prompts-zh

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

LLM-Finetuning-Toolkit

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

munch

A Munch is a Python dictionary that provides attribute-style access (a la JavaScript objects).

pyautogui

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

LoRA-ViT

Low rank adaptation for Vision Transformer

zero-copy-model-loading

In-depth code associated with my Medium blog post, "How to Load PyTorch Models 340 Times Faster with Ray"

piqa

PyTorch Image Quality Assessement package

pytorch-ssim

pytorch structural similarity (SSIM) loss

pytorch-msssim

Fast and differentiable MS-SSIM and SSIM for pytorch.

unsplit

Supplementary code for the paper "UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning".

AIJack

Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)

Alpha-Shop

awesome-split-learning

A curated repository for various papers in the domain of split learning.

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

test

Measuring Massive Multitask Language Understanding | ICLR 2021

FedPETuning

FastChat

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

TextAttack

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

PiPPy

Pipeline Parallelism for PyTorch

jupiter

RISC-V Assembler and Runtime Simulator

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

llama.cpp

LLM inference in C/C++

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

bitsandbytes

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

Table-Pretraining

ICLR 2022 Paper, SOTA Table Pre-training Model, TAPEX: Table Pre-training via Learning a Neural SQL Executor