lunar

pyre-code. A self-hosted ML coding practice platform. 68 problems from ReLU to flow matching — attention, training, RLHF, diffusion, and more. Instant feedback in the browser.

Awesome-Agent-Harness. Agent Harness for Large Language Model Agents: A Survey. Survey on LLM agentharnessengineering with a taxonomy. 110+papers, 23 systems analyzed.

learn-coding-agent. Research on Coding Agents

xhs-cli. 小红书命令行工具 — 搜索、阅读、点赞、收藏、评论，全在终端完成 | Xiaohongshu CLI

AI-Video-Transcriber. Transcribe and summarize videos and podcasts using AI. Open-source, multi-platform, and supports multiple languages.

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

py-spy. Sampling profiler for Python programs

AutoJs6. 安卓平台 JavaScript 自动化工具 (Auto.js 二次开发项目)

open-r1. Fully open reproduction of DeepSeek-R1

Logic-RL. Reproduce R1 Zero on Logic Puzzle

arXiv_recbot. A Telegram bot to recommend arXiv papers

docling. Get your documents ready for gen AI

youtube-summarizer-oss. Finally, an open source Youtube Summarizer extension

fish-speech. SOTA Open Source TTS

markdown-online-editor. 📝 基于 Vue2、Vditor，所构建的在线 Markdown 编辑器，支持绘制流程图、甘特图、时序图、任务列表、echarts 图表、五线谱，以及 PPT 预览、视频音频解析、HTML 自动转换为 Markdown 等功能。https://www.niceshare.site

kotaemon. An open-source RAG-based tool for chatting with your documents.

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

LLM-Merging. LLM-Merging: Building LLMs Efficiently through Merging

Vript. Python

chunkit. Convert URLs into LLM-friendly markdown chunks

RAG_Techniques. This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.

Vane. Vane is an AI-powered answering engine.

awesome-english-ebooks. 经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

firecrawl. The API to search, scrape, and interact with the web at scale. 🔥

MeloTTS. High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.

torchtune. PyTorch native post-training library

ChatTTS. A generative speech model for daily dialogue.

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

hh-rlhf. Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

alignment-handbook. Robust recipes to align language models with human and AI preferences

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

HanLP. 中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

distilabel. Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

lobehub. 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

chat-ui. The open source codebase powering HuggingChat

textgen. Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

EasyEdit. [ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

GPT-SoVITS. 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

laion5b-downloader. Python

SillyTavern. LLM Frontend for Power Users.

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

mergekit. Tools for merging pretrained large language models.

selfcheckgpt. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

MetaGPT. 🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

llm-foundry. LLM training code for Databricks foundation models

dolma. Data and tools for generating and inspecting OLMo pre-training data.

DRUGS. Stop messing around with finicky sampling parameters and just use DRµGS!

algorithmic-efficiency. MLCommons Algorithmic Efficiency is a benchmark and competition measuring neural network training speedups due to algorithmic improvements in both training algorithms and models.

Safety-Prompts. Chinese safety prompts for evaluating and improving the safety of LLMs. 中文安全prompts，用于评估和提升大模型的安全性。

zeroshot-classifier. Notebooks for training universal 0-shot classifiers on many different tasks

MBP. MBP: Multi-task Bioassay Pre-training for Protein-Ligand Binding Affinity Prediction

lm-inference-engines. Comparison of Language Model Inference Engines

exllamav2. A fast inference library for running LLMs locally on modern consumer-class GPUs

bitsandbytes. Accessible large language models via k-bit quantization for PyTorch.

torchdistill. A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

ragas. Supercharge Your LLM Application Evaluations 🚀

Awesome-GPTs. Curated list of awesome GPTs 👍.

Pytorch-Memory-Utils. pytorch memory track code

MultiInstruct. MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning

Megatron-LLaMA. Best practice for training LLaMA models in Megatron-LM

Awesome-LLM-Inference. 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

List-of-Dirty-Naughty-Obscene-and-Otherwise-Bad-Words. List of Dirty, Naughty, Obscene, and Otherwise Bad Words

deduplicate-text-datasets. Rust

ChatGPT_Agent. A Game Demo Powered by ChatGPT Agents

llmboxing. LLM boxing matches

llm3s-conatiner. large language model training-3-stages+deployment

OpenBuddy. Open Multilingual Chatbot for Everyone

AgentTuning. AgentTuning: Enabling Generalized Agent Abilities for LLMs

WizardLM. LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

h2o-wizardlm. Open-Source Implementation of WizardLM to turn documents into Q:A pairs for LLM fine-tuning

opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Xwin-LM. Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

dotfiles-public. My personal dotfiles

LunarVim. 🌙 LunarVim is an IDE layer for Neovim. Completely free and community driven.

nougat. Implementation of Nougat Neural Optical Understanding for Academic Documents

WanJuan1.0. 万卷1.0多模态语料

burn. Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

cc2dataset. Easily convert common crawl to a dataset of caption and document. Image/text Audio/text Video/text, ...

Firefly. Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

SuperAdapters. Finetune ALL LLMs with ALL Adapeters on ALL Platforms!

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

top-1m-domains. 🌐 List of free and downloadable top 1M domain list (alexa alternatives) 📊

helm. Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

qlora. QLoRA: Efficient Finetuning of Quantized LLMs

Megatron-LM. Ongoing research training transformer models at scale

SpQR. Python

modelzoo. Python

AutoGPTQ. An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

lm-evaluation-harness. A framework for few-shot evaluation of language models.

lm-evaluation. Evaluation suite for large-scale language models.

a1111-sd-webui-lycoris. An extension for stable-diffusion-webui to load lycoris models.

ONE-PEACE. A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

chain-of-thought-hub. Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Chinese-LLaMA-Alpaca. 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

wtf_wikipedia. a pretty-committed wikipedia markup parser

bark. 🔊 Text-Prompted Generative Audio Model

BELLE. BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

StableLM. StableLM: Stability AI Language Models

data-preparation. Code used for sourcing and cleaning the BigScience ROOTS corpus

RedPajama-Data. The RedPajama-Data repository contains code for preparing large datasets for training large language models.

GPTCache. Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

MNBVC. MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

CDCS. Chinese Data Competitions' Solutions

diffusion-deploy. Python

llama. Inference code for Llama models

LiveSpeechPortraits. Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

html2text. Convert HTML to Markdown-formatted text.

ChatGPT. Reverse engineered ChatGPT API

natural-instructions. Expanding natural instructions

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

OFA. Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

jellyfin. The Free Software Media System - Server Backend & API

jsoncrack.com. ✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML and CSV into interactive graphs.

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

MusicPlayer2. MusicPlayer2是一款功能强大的本地音乐播放软件，旨在为用户提供最佳的本地音乐播放体验。它支持歌词显示、歌词卡拉OK样式显示、歌词在线下载、歌词编辑、歌曲标签识别、专辑封面显示、专辑封面在线下载、频谱分析、音效设置、任务栏缩略图按钮、主题颜色、格式转换等功能，支持高度自定义的界面布局，支持多种播放内核（BASS和FFMpeg）。播放器支持大部分常见的音频格式。

pytorch-fid. Compute FID scores with PyTorch.

the-art-of-command-line. Master the command line, in one page

flash-attention. Fast and memory-efficient exact attention

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Awesome-Model-Quantization. A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

Data-Science-Cheatsheet. TeX

stable-diffusion. A latent text-to-image diffusion model

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

PPASR. 基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Machine-Learning-Practice. To polish up my understanding of the course of ML.

geekinglcq.

jane_street. Jupyter Notebook

movies. HTML

zipr.

zhi.

trace. Python

NLP4fun. Python

Hiho. C++

awesome-production-machine-learning. A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

OpenBB. Open Data Platform for analysts, quants and AI agents.

GLM-130B. GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

CKA.pytorch. A PyTorch implementation of Centered Kernel Alignment (CKA) with GPU acceleration.

bottom. Yet another cross-platform graphical process/system monitor.

dust. A more intuitive version of du in rust

subspace-match. Python

ext-saladict. 🥗 All-in-one professional pop-up dictionary and page translator which supports multiple search modes, page translations, new word notebook and PDF selection searching.

weekly. 科技爱好者周刊，每周五发布

WantWords. An open-source online reverse dictionary.

MQBench. Model Quantization Benchmark

papers-we-love. Papers from the computer science community to read and discuss.

HowToLiveLonger. 程序员延寿指南 | A programmer's guide to live longer

paper-reading. 深度学习经典、新论文逐段精读

run. 润学全球官方指定GITHUB，整理润学宗旨、纲领、理论和各类润之实例；解决为什么润，润去哪里，怎么润三大问题； 并成为新中国人的核心宗教，核心信念。

luoxi_models. see readme

HRec. Heterogeneous Recommendation

TextBrewer. A PyTorch-based knowledge distillation toolkit for natural language processing

flair. A very simple framework for state-of-the-art Natural Language Processing (NLP)

tner. Language model fine-tuning on NER with an easy interface and cross-domain evaluation. "T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition, EACL 2021"

bt-qinglong-nolanjdc-xdd. 整理出一套适合小白的教程

greykite. A flexible, intuitive and fast forecasting library

jupyter_ascending. Ascend your Jupyter Notebook usage

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

AugLy. A data augmentations library for audio, image, text, and video.

jupytext. Jupyter Notebooks as Markdown Documents, Julia, Python or R scripts

pretrain-gnns. Strategies for Pre-training Graph Neural Networks

atom3d. ATOM3D: tasks on molecules in three dimensions

Transformers4Rec. Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.

animegan2-pytorch. PyTorch implementation of AnimeGANv2

MGSSL. Official implementation of NeurIPS'21 paper"Motif-based Graph Self-Supervised Learning for Molecular Property Prediction"

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

pycaret. Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.

gym. A toolkit for developing and comparing reinforcement learning algorithms.

free-programming-books. :books: Freely available programming books

anonymous_github. Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

speechbrain. A PyTorch-based Speech Toolkit

iptv. Collection of publicly available IPTV channels from all over the world

fastmoe. A fast MoE impl for PyTorch

vnpy. 基于Python的开源量化交易平台开发框架

awesome-python-applications. 💿 Free software that works great, and also happens to be open-source Python.

playwright-python. Python version of the Playwright testing and automation library.

hexo-theme-hueman. A redesign of Alx's wordpress theme Hueman, ported to Hexo.

hexo-theme-butterfly. 🦋 A Hexo Theme: Butterfly

fairchem. FAIR Chemistry's library of machine learning methods for chemistry

talking-head-anime-demo. Demo for the "Talking Head Anime from a Single Image."

spectra-review-paper-competition. Competition for best expository article on cutting-edge ML research

ticker. Track stocks, crypto, and derivatives prices and positions in real time from your terminal

AudioDVP. AudioDVP:Photorealistic Audio-driven Video Portraits

NeuRec. Next RecSys Library

daisyRec. Official code for "DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation" (TPAMI2022) and "Are We Evaluating Rigorously? Benchmarking Recommendation for Reproducible Evaluation and Fair Comparison" (RecSys2020)

public-apis. A collective list of free APIs

system-design-primer. Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

MML-Book. Code / solutions for Mathematics for Machine Learning (MML Book)

PUbiasedN. PyTorch implementation for the paper Classification from Positive, Unlabeled and Biased Negative Data.

Alchemy. Python

Tech_Aarticle. 主要是我是日常看过的不错的文章的资源汇总，方便自己也分享给大家。有些我看过的，就会做简单的解读，没看过的，就先罗列一下，然后之后看了把解读更新上；涉及到搜索/推荐/自然语言处理。

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

imbalanced-learn. A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

spotify-sequential-skip-prediction. 7th place solution to the WSDM Cup 2019 - Spotify - Sequential Skip Prediction Challenge

sequential-skip-prediction. Source code for our approach to the 2019 WSDM Cup Spotify Sequential Skip Prediction Challenge

AS_Molecule. Active learning