Rui Xu's starred repositories

PowerToys

Windows system utilities to maximize productivity

llama

Inference code for LLaMA models

Language:PythonLicense:NOASSERTIONStargazers:50895Issues:499Issues:872

ColossalAI

Making large AI models cheaper, faster and more accessible

Language:PythonLicense:Apache-2.0Stargazers:38577Issues:384Issues:1648

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Language:PythonLicense:Apache-2.0Stargazers:34624Issues:343Issues:2708

setup-ipsec-vpn

Scripts to build your own IPsec VPN server, with IPsec/L2TP, Cisco IPsec and IKEv2

Language:ShellLicense:NOASSERTIONStargazers:24892Issues:649Issues:1443

mamba

Mamba SSM architecture

Language:PythonLicense:Apache-2.0Stargazers:12447Issues:102Issues:491

PRML

PRML algorithms implemented in Python

Language:Jupyter NotebookLicense:MITStargazers:11382Issues:419Issues:24

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:8772Issues:116Issues:115

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Language:PythonLicense:NOASSERTIONStargazers:8639Issues:148Issues:1561

OpenPrompt

An Open-Source Framework for Prompt-Learning.

Language:PythonLicense:Apache-2.0Stargazers:4291Issues:43Issues:256

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Language:PythonLicense:Apache-2.0Stargazers:4107Issues:33Issues:1321

glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

Language:PythonLicense:MITStargazers:3523Issues:165Issues:44

torchscale

Foundation Architecture for (M)LLMs

Language:PythonLicense:MITStargazers:2997Issues:46Issues:76

QuantsPlaybook

量化研究-券商金工研报复现

Language:Jupyter NotebookStargazers:2550Issues:77Issues:5

s4

Structured state space sequence models

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2346Issues:52Issues:133

wavenet_vocoder

WaveNet vocoder

Language:PythonLicense:NOASSERTIONStargazers:2311Issues:96Issues:193

prml

Repository of notes, code and notebooks in Python for the book Pattern Recognition and Machine Learning by Christopher Bishop

Language:Jupyter NotebookLicense:AGPL-3.0Stargazers:2067Issues:33Issues:0

Poker

Fully functional Pokerbot that works on PartyPoker, PokerStars and GGPoker, scraping tables with Open-CV (adaptable via gui) or neural network and making decisions based on a genetic algorithm and montecarlo simulation for poker equity calculation. Binaries can be downloaded with this link:

Language:PythonLicense:GPL-3.0Stargazers:1993Issues:142Issues:150

EasyCV

An all-in-one toolkit for computer vision

Language:PythonLicense:Apache-2.0Stargazers:1754Issues:31Issues:75

mmflow

OpenMMLab optical flow toolbox and benchmark

Language:PythonLicense:Apache-2.0Stargazers:949Issues:7Issues:71

mixture-of-experts

PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538

Language:PythonLicense:GPL-3.0Stargazers:934Issues:5Issues:26

mixture-of-experts

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

Language:PythonLicense:MITStargazers:605Issues:6Issues:11

Beijing-House

面向北京码农同胞的从0开始的买房踩盘实录,目标只有一个: 每一分钱都花的明白(持续补充和完善ing…)

HorNet

[NeurIPS 2022] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions

Language:PythonLicense:MITStargazers:314Issues:5Issues:37

RetNet

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

Language:Jupyter NotebookLicense:MITStargazers:225Issues:5Issues:31

ccnn

Code repository of the paper "Modelling Long Range Dependencies in ND: From Task-Specific to a General Purpose CNN" https://arxiv.org/abs/2301.10540.

Language:PythonLicense:MITStargazers:178Issues:4Issues:11

mTAN

Code for "Multi-Time Attention Networks for Irregularly Sampled Time Series", ICLR 2021.

Language:PythonLicense:MITStargazers:113Issues:3Issues:8

RepSR

Codes for "RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization"

dks

Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.

Language:PythonLicense:Apache-2.0Stargazers:57Issues:5Issues:0

RBP_Pose

pytorch implementation of RBP-Pose