Junjie Qiu's repositories
transformer-reproduction
A Pytorch reproduction of "Attention is all you need".
Haro-Archive
Open archive of Harold QIU.
CS102A-Chess
A Java Chess project that supports online gaming and online chatting for CS102A 2022, SUSTech.
Haro-Toys
Source of toy projects
NotionNext
Personal Blog
RAYPool
An easy to implement high-throughput offline inference strategy for LLMs
CPOOD
A simple OOD detection method based on conformal learning
resume
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
wanda
A simple and effective LLM pruning approach.
DeepSpeed-MII
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Hadoop-Project
2023年秋季-分布式存储与计算-课程Project
TorchCP
A Python toolbox for conformal prediction research on deep learning models, using PyTorch.
ASC24-LLM-inference-optimization
The dataset and baseline code for ASC23 LLM inference optimization challenge.
llama
Inference code for LLaMA models
random-fourier-features
Implementation of random Fourier features for kernel method, like support vector machine and Gaussian process model
XAgent
An Autonomous LLM Agent for Complex Task Solving