sosofun's repositories
ColossalAI
Making big AI models cheaper, easier, and more scalable
annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Beijing-IPTV
最好用的北京联通、北京移动IPTV频道列表。https://bjiptv.gq/
best_AI_papers_2021
A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code. [work in progress]
croc
Easily and securely send things from one computer to another :crocodile: :package:
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
fastapi-web-template
a web project template based on fastapi and sqlalchemy2
first-contributions
🚀✨ Help beginners to contribute to open source projects
gemma-chinese
Finetune Gemma for Chinese
gemma-sft
Gemma-SFT, gemma-2b/gemma-7b微调(finetune,transformers)/LORA(peft)/推理(inference)
gin-vue-admin
基于vite+vue3+gin搭建的开发基础平台，集成jwt鉴权，权限管理，动态路由，分页封装，多点登录拦截，资源权限，上传下载，代码生成器，表单生成器等开发必备功能，五分钟一套CURD前后端代码。
iptv
Collection of publicly available IPTV channels from all over the world
joplin
Joplin - an open source note taking and to-do application with synchronization capabilities for Windows, macOS, Linux, Android and iOS. Forum: https://discourse.joplinapp.org/
Langchain-Chatchat
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
lion-pytorch
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
loguru
Python logging made (stupidly) simple
MAmmoTH
This repo contains the code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning"
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
PERSIA
High performance distributed framework for training deep learning recommendation models based on PyTorch.
qmoe
Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
rerope
Rectified Rotary Position Embeddings
rust-course
“连续六年成为全世界最受喜爱的语言，无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。<<Rust语言圣经>>拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，甚至还有JS程序员关注的 WASM 和 Deno 等专题。这可能是目前最用心的 Rust 中文学习教程 / Book
rustlings
:crab: Small exercises to get you used to reading and writing Rust code!
semi-design
A modern, comprehensive, flexible design system and React UI library
system-design-101
Explain complex systems using visuals and simple terms. Help you prepare for system design interviews.
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
X6
🚀 JavaScript diagramming library that uses SVG and HTML for rendering.
yarn
YaRN: Efficient Context Window Extension of Large Language Models