Starred repositories
A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
A beginner friendly Obsidian vault template.
benchmarking large language models (LLMs) with a focus on their mathematical capabilities
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
A comprehensive toolkit for podcast evaluation. https://arxiv.org/abs/2510.00485
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
Towards Deep Audio Reasoning in Large Audio Language Models
3
Updated Jul 3, 2026
中央空调 VRF 网关 Esphome 组件，支持小米平头熊 PTXZN 和德姆瑞 Demry 两款中央空调网关
中央空调网关 VRF ESPHome 串口通信固件。支持德姆瑞DEMRY、平头熊PTXZN、中弘系列。
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
Xiaomi Home Integration for Home Assistant
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
DFlash: Block Diffusion for Flash Speculative Decoding
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
VoiceGrad DPM+BNF is a non-parallel any-to-many voice conversion framework built on Diffusion Probabilistic Modeling, score matching, annealed Langevin dynamics, and Bottleneck Feature conditioning…
Repository of lessons exploring image diffusion models, focused on understanding and education.
SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models
nano-vllm是开源的一个gpu推理项目，基于开源版本弄的一个ascend npu版本推理小demo，旨在帮助初学者了解推理的整体流程，区别于vllm，nano-vllm体量更小，麻雀虽小五脏俱全，更有助于初学者学习。
A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visual…
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
收集全网 Android TV电视盒子应用，涵盖影视、直播、K歌、工具、游戏等类型，整理优质APK资源，支持便捷下载与自动更新。提供安全验证、分类索引与兼容性标注，助力用户打造家庭影音娱乐中心！ ✅ TVBox/影视仓等影音壳接口配置源。
收集各大AndroidTV的apk应用，可免费看vip和国外电影电视。如大家有也可以贡献一下。
MOSS-Audio is an open-source foundation model for unified audio understanding, enabling speech, sound, music, captioning, QA, and reasoning in real-world scenarios.
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.