闲来无事逛github发现一些好玩的大模型项目，给大家分享一下。
1 训练篇
1.1 LLaMA-Factory – 23.1k stars
该项目一个字，“牛”，两个字，“顶级”。基本上囊括了市面上基本的训练方式和算法，以及一些扩展方面，适用于模型可视化训练。
- Various models: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
- Integrated methods: (Continuous) pre-training, (multimodal) supervised fine-tuning, reward modeling, PPO, DPO, KTO and ORPO.
- Scalable resources: 32-bit full-tuning, 16-bit freeze-tuning, 16-bit LoRA and 2/4/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8.
- Advanced algorithms: GaLore, BAdam, DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ and Agent tuning.
- Practical tricks: FlashAttention-2, Unsloth, RoPE scaling, NEFTune and rsLoRA.
- Experiment monitors: LlamaBoard, TensorBoard, Wandb, MLflow, etc.
- Faster inference: OpenAI-style API, Gradio UI and CLI with vLLM worker.
2.2 Open WebUI – 24.1k stars
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs
一个前端页面，可以通过后端接口连接到LLM，方便配合Ollama使用。
2.4 Chat-on-wechat – 26.4k stars
chatgpt-on-wechat（简称CoW）项目是基于大模型的智能对话机器人，支持微信公众号、企业微信应用、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/Gemini/LinkAI/ChatGLM/KIMI/文心一言/讯飞星火/通义千问/LinkAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。
2.5 Dify – 31.1k stars
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
一个联合LLM和RAG功能的平台，可以实现RAG、大模型工作流，Agent等功能，可配合Ollama使用。
2.6 llama_index – 32.1k stars
LlamaIndex (GPT Index) is a data framework for your LLM application. Building with LlamaIndex typically involves working with LlamaIndex core and a chosen set of integrations (or plugins).
用于快速搭建RAG的项目，可以配合Langchain使用。
2.7 OpenDevin – 26.4k stars
Welcome to OpenDevin, a platform for autonomous software engineers, powered by AI and LLMs.
OpenDevin agents collaborate with human developers to write code, fix bugs, and ship features.
2 资料篇
2.1 Awesome Chinese LLM – 11.9k stars
自ChatGPT为代表的大语言模型（Large Language Model, LLM）出现以后，由于其惊人的类通用人工智能（AGI）的能力，掀起了新一轮自然语言处理领域的研究和应用的浪潮。尤其是以ChatGLM、LLaMA等平民玩家都能跑起来的较小规模的LLM开源之后，业界涌现了非常多基于LLM的二次微调或应用的案例。本项目旨在收集和梳理中文LLM相关的开源模型、应用、数据集及教程等资料，目前收录的资源已达100+个！
2.2 llm-course – 31.7k stars
大模型就业者必经网站。
The LLM course is divided into three parts:
- 🧩 LLM Fundamentals covers essential knowledge about mathematics, Python, and neural networks.
- 🧑🔬 The LLM Scientist focuses on building the best possible LLMs using the latest techniques.
- 👷 The LLM Engineer focuses on creating LLM-based applications and deploying them.