Zhenheng TANG's repositories
awesome-decentralized-llm
Collection of LLM resources that can be used to build products you can "own" or to perform reproducible research.
baby-llama2-chinese
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
BMCook
Model Compression for Big Models
BudgetCL
Code for CVPR paper: Computationally Budgeted Continual Learning: What Does Matter?
cifar10-fast-simple
Train CIFAR10 to 94% accuracy in a few minutes/seconds. Based on https://github.com/davidcpage/cifar10-fast
DenoisingDiffusionProbabilityModel-ddpm-
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
EMP-SSL
This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."
FederatedScope
An easy-to-use federated learning platform
flower
Flower - A Friendly Federated Learning Framework
GBLM-Pruner
Are gradient information useful for pruning of LLMs?
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
hlb-CIFAR10
Train to 94% on CIFAR-10 in less than 10 seconds on a single A100, the current world record. Or ~95.77% in ~188 seconds.
LLM-RLHF-Tuning
LLM Tuning with PEFT (SFT+RM+PPO with LoRA)
LotteryFL
LotteryFL: Empower Edge Intelligence with Personalized and Communication-Efficient Federated Learning (2021 IEEE/ACM Symposium on Edge Computing)
MiniGPT-4
Open-sourced codes for MiniGPT-4 and MiniGPT-v2
msrflute
Federated Learning Utilities and Tools for Experimentation
rome
Locating and editing factual associations in GPT (NeurIPS 2022)
SciencePlots
Matplotlib styles for scientific plotting
Time-Series-Library
A Library for Advanced Deep Time Series Models.
wizard1203.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes