Weigao Sun (weigao266)

weigao266

Geek Repo

Location:Shanghai, China

Github PK Tool:Github PK Tool

Weigao Sun's starred repositories

FasterTransformer

Transformer related optimization, including BERT, GPT

Language:C++License:Apache-2.0Stargazers:5708Issues:0Issues:0

FastPointTransformer

Official source code of Fast Point Transformer, CVPR 2022

Language:PythonLicense:MITStargazers:264Issues:0Issues:0

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Language:PythonLicense:NOASSERTIONStargazers:1783Issues:0Issues:0

FlagAttention

A collection of memory efficient attention operators implemented in the Triton language.

Language:PythonLicense:NOASSERTIONStargazers:193Issues:0Issues:0

LightSeq

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

Language:PythonStargazers:170Issues:0Issues:0
Language:PythonLicense:NOASSERTIONStargazers:70Issues:0Issues:0

llm-numbers

Numbers every LLM developer should know

Stargazers:4023Issues:0Issues:0

pymobiledevice3

Pure python3 implementation for working with iDevices (iPhone, etc...).

Language:PythonLicense:GPL-3.0Stargazers:1232Issues:0Issues:0

Megatron-LLaMA

Best practice for training LLaMA models in Megatron-LM

Language:PythonLicense:NOASSERTIONStargazers:583Issues:0Issues:0

nccl-tests

NCCL Tests

Language:CudaLicense:BSD-3-ClauseStargazers:776Issues:0Issues:0

DinkyTrain

Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃

Language:PythonLicense:MITStargazers:111Issues:0Issues:0
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:17Issues:0Issues:0

TclPyHyperWorks

基于hyperworks (hypermesh & hyperview) 的二次开发相关,TCL为主,部分python

Language:TclStargazers:31Issues:0Issues:0

matplotlib-gallery

Examples of matplotlib codes and plots

Language:Jupyter NotebookLicense:GPL-3.0Stargazers:1176Issues:0Issues:0

SuperAGI

<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

Language:PythonLicense:MITStargazers:15092Issues:0Issues:0

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Language:PythonLicense:MITStargazers:35420Issues:0Issues:0

dadaptation

D-Adaptation for SGD, Adam and AdaGrad

Language:PythonLicense:MITStargazers:493Issues:0Issues:0

TransnormerLLM

Official implementation of TransNormerLLM: A Faster and Better LLM

Language:PythonLicense:Apache-2.0Stargazers:222Issues:0Issues:0

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

Language:HTMLLicense:Apache-2.0Stargazers:8370Issues:0Issues:0

uvadlc_notebooks

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

Language:Jupyter NotebookLicense:MITStargazers:2378Issues:0Issues:0

chatgpt-prompts-for-academic-writing

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

Stargazers:2680Issues:0Issues:0

Transformer-Evolution-Paper

记录Transformer升级的论文笔记

Stargazers:17Issues:0Issues:0

Awesome-Chinese-LLM

整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。

Stargazers:13990Issues:0Issues:0

cs-video-courses

List of Computer Science courses with video lectures.

Stargazers:66192Issues:0Issues:0

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Stargazers:9124Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:42Issues:0Issues:0

fairscale

PyTorch extensions for high performance and large scale training.

Language:PythonLicense:NOASSERTIONStargazers:3103Issues:0Issues:0

iTerm2-Color-Schemes

Over 250 terminal color schemes/themes for iTerm/iTerm2. Includes ports to Terminal, Konsole, PuTTY, Xresources, XRDB, Remmina, Termite, XFCE, Tilda, FreeBSD VT, Terminator, Kitty, MobaXterm, LXTerminal, Microsoft's Windows Terminal, Visual Studio, Alacritty

Language:ShellLicense:NOASSERTIONStargazers:24508Issues:0Issues:0

wikiextractor

A tool for extracting plain text from Wikipedia dumps

Language:PythonLicense:AGPL-3.0Stargazers:3707Issues:0Issues:0