Starred repositories
程序员在家做饭方法指南。Programmer's guide about how to cook at home (Simplified Chinese only).
Building Large Language Model Applications, Published by Packt
A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".
Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
✨✨Latest Advances on Multimodal Large Language Models
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Simple, unified interface to multiple Generative AI providers
LLMs-from-scratch项目中文翻译
A full-featured, hackable Next.js AI chatbot built by Vercel
📙《高并发的哲学原理》开源图书(CC BY-NC-ND)https://pphc.lvwenhan.com
基于 ChatGPT API 的划词翻译浏览器插件和跨平台桌面端应用 - Browser extension and cross-platform desktop application for translation based on ChatGPT API.
An open-source RAG-based tool for chatting with your documents.
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
Understanding Deep Learning - Simon J.D. Prince
Open Immersive Translate. A revolutionary open-source browser translation plugin that enables everyone to have a native-like reading experience. 开源的沉浸式翻译,一款革命性的浏览器翻译插件,让所有人都能够拥有母语般的阅读体验。
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
一个基于 AI 的 Hacker News 中文播客项目,每天自动抓取 Hacker News 热门文章,通过 AI 生成中文总结并转换为播客内容。
AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
LLM based autonomous agent that conducts deep local and web research on any topic and generates a long report with citations.
Google Research
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…
Question and Answer based on Anything.
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows