{"id":26896794,"url":"https://github.com/echonoshy/cgft-llm","last_synced_at":"2025-04-01T04:02:02.431Z","repository":{"id":260121585,"uuid":"804246381","full_name":"echonoshy/cgft-llm","owner":"echonoshy","description":"Practice to LLM.","archived":false,"fork":false,"pushed_at":"2025-03-29T17:05:20.000Z","size":28882,"stargazers_count":1215,"open_issues_count":0,"forks_count":175,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-03-29T18:20:20.969Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/echonoshy.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-22T08:26:05.000Z","updated_at":"2025-03-29T17:05:25.000Z","dependencies_parsed_at":"2025-01-05T11:19:21.841Z","dependency_job_id":"e53bb554-25f7-4c6e-9f4a-b78ee156c4e1","html_url":"https://github.com/echonoshy/cgft-llm","commit_stats":null,"previous_names":["echonoshy/cgft-llm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/echonoshy%2Fcgft-llm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/echonoshy%2Fcgft-llm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/echonoshy%2Fcgft-llm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/echonoshy%2Fcgft-llm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/echonoshy","download_url":"https://codeload.github.com/echonoshy/cgft-llm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246580463,"owners_count":20800110,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-01T04:02:00.461Z","updated_at":"2025-04-01T04:02:02.405Z","avatar_url":"https://github.com/echonoshy.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","Learning and Reference"],"sub_categories":["Tutorials and Books"],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/logo-min.png\" width=\"580\" alt=\"Hands on LLMs\"/\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n  ![GitHub stars](https://img.shields.io/github/stars/echonoshy/cgft-llm?style=social)\n  ![GitHub forks](https://img.shields.io/github/forks/echonoshy/cgft-llm?style=social)\n  ![GitHub watchers](https://img.shields.io/github/watchers/echonoshy/cgft-llm?style=social)\n  ![GitHub repo size](https://img.shields.io/github/repo-size/echonoshy/cgft-llm)\n  ![GitHub language count](https://img.shields.io/github/languages/count/echonoshy/cgft-llm)\n  ![GitHub top language](https://img.shields.io/github/languages/top/echonoshy/cgft-llm)\n  ![GitHub last commit](https://img.shields.io/github/last-commit/echonoshy/cgft-llm?color=red)\n  \n\u003c/div\u003e\n\n\n# ⛰️ 动手做大模型系列 🎮\n\n如果你在实操的过程中遇到问题，请在对应的视频下方留言。\n复现遇到bug，请描述：\n1. 🎯 运行环境\n2. 🧩 对应的代码、日志和报错截图\n\n有感兴趣的内容或问题，[点击这里加入讨论🎉](https://github.com/echonoshy/cgft-llm/discussions)。\n\n\u003e 如果你不太了解如何提出一个好问题，请花几分钟阅读一下这个，相信我，可能并不能改变什么🤫（不是）。  \n\u003e [How-To-Ask-Questions-The-Smart-Way](https://github.com/ryanhanwu/How-To-Ask-Questions-The-Smart-Way/blob/main/README-zh_CN.md)  \n\n\n\n## 🔬 视频及文档合集\n\n### ⚡ 1. 大模型核心技术\n\n| 序号 | 项目 | 代码文档 | 视频时长 | 视频教程 |\n|------|------|----------|----------|----------|\n| 1 | 使用llama-factory微调llama3 | [llama-factory](llama-factory/README.md) | ![Duration](https://img.shields.io/badge/Duration-35:28-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1uw4m1S7Cd)](https://www.bilibili.com/video/BV1uw4m1S7Cd/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/Hpc4QQQuLWM?style=social)](https://youtu.be/Hpc4QQQuLWM) |\n| 2 | 训练数据整理以及微调优化建议 | [training-dataset](docs/llama-factory-training-dataset.md) | ![Duration](https://img.shields.io/badge/Duration-20:13-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1vrksYgEP9)](https://www.bilibili.com/video/BV1vrksYgEP9) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/tOVG1YZ9bcI?style=social)](https://youtu.be/tOVG1YZ9bcI) |\n| 3 | llama.cpp进行轻量化部署和量化 | [llama-cpp](llama-cpp/README.md) | ![Duration](https://img.shields.io/badge/Duration-46:37-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1et421N7TK)](https://www.bilibili.com/video/BV1et421N7TK) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/2MYsfe0pc9A?style=social)](https://youtu.be/2MYsfe0pc9A) |\n| 4 | ollama大模型部署工具介绍 | [ollama](docs/ollama-introduction.md) | ![Duration](https://img.shields.io/badge/Duration-21:28-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1Gs421u7a5)](https://www.bilibili.com/video/BV1Gs421u7a5/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/yQ1q8YWacyE?style=social)](https://youtu.be/yQ1q8YWacyE) |\n| 5 | vllm部署工具及paged attention | [vllm](vllm/README.md) | ![Duration](https://img.shields.io/badge/Duration-40:28-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1R1421r7tk)](https://www.bilibili.com/video/BV1R1421r7tk) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/cQWzKX9gM9Q?style=social)](https://youtu.be/cQWzKX9gM9Q) |\n| 6 | llama-index实现RAG | [llama-index](llama-index/README.md) | ![Duration](https://img.shields.io/badge/Duration-21:48-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1jE421A77u)](https://www.bilibili.com/video/BV1jE421A77u) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/Q6vUx94HCDc?style=social)](https://youtu.be/Q6vUx94HCDc) |\n| 7 | graph-rag本地部署 | [graph-rag](graph-rag/README.md) | ![Duration](https://img.shields.io/badge/Duration-23:23-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1rE421w7t3)](https://www.bilibili.com/video/BV1rE421w7t3) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/tFLJUXsKGsc?style=social)](https://youtu.be/tFLJUXsKGsc) |\n| 8 | mkdocs+readthedocs部署项目文档 | [mkdocs](docs/mkdocs.md) | ![Duration](https://img.shields.io/badge/Duration-11:25-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV19f421v7P9)](https://www.bilibili.com/video/BV19f421v7P9) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/FRyvV-hj65M?style=social)](https://youtu.be/FRyvV-hj65M) |\n| 9 | function-calling 自动发邮件 | [function-calling](function-calling/README.md) | ![Duration](https://img.shields.io/badge/Duration-23:10-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1eH4y1c7KQ)](https://www.bilibili.com/video/BV1eH4y1c7KQ/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/U2tbBxtA_wQ?style=social)](https://youtu.be/U2tbBxtA_wQ) |\n| 10 | 大模型学习路径及面试 | [llm-roadmap](docs/llm-roadmap.md) | ![Duration](https://img.shields.io/badge/Duration-25:01-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1maW4euELX)](https://www.bilibili.com/video/BV1maW4euELX) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/-YLeUO6wwz8?style=social)](https://youtu.be/-YLeUO6wwz8) |\n| 11 | 大模型算法岗非技术答疑 | [llm-no-tec-qa](docs/llm-no-tec-qa.md) | ![Duration](https://img.shields.io/badge/Duration-16:00-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1Kjx7ejE5M)](https://www.bilibili.com/video/BV1Kjx7ejE5M/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/JrY8CL0pz68?style=social)](https://youtu.be/JrY8CL0pz68) |\n| 12 | AI标注流程及label studio框架 | [label-studio](docs/label-studio.md) | ![Duration](https://img.shields.io/badge/Duration-20:00-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1oRxteFEJi)](https://www.bilibili.com/video/BV1oRxteFEJi) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/rTNrfq5Ay7o?style=social)](https://youtu.be/rTNrfq5Ay7o) |\n| 13 | AI算法项目开发流程及实例 | [AI-project-workflow](docs/AI项目开发流程.pdf) | ![Duration](https://img.shields.io/badge/Duration-34:43-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1XSUpYmERX)](https://www.bilibili.com/video/BV1XSUpYmERX) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/dB9t3fcuVF8?style=social)](https://youtu.be/dB9t3fcuVF8) |\n| 14 | dify实现Agent和LLM Workflow | [agent-llm-workflow](docs/dify-agent-llm-workflow.md) | ![Duration](https://img.shields.io/badge/Duration-59:23-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1hacaeNEQJ)](https://www.bilibili.com/video/BV1hacaeNEQJ) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/zU5nHsUx5ck?style=social)](https://youtu.be/zU5nHsUx5ck) |\n| 15 | rpa自动化结合LLM workflow | [rpa-automation](docs/rpa-automation-with-llm-agent.md) | ![Duration](https://img.shields.io/badge/Duration-13:20-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1qcNUeNEXf)](https://www.bilibili.com/video/BV1qcNUeNEXf) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/Y7b0RVVO6QI?style=social)](https://youtu.be/Y7b0RVVO6QI) |\n| 16 | deepseek-r1模型微调和训练数据构造 | [deepseek-r1-finetune](docs/deepseek-r1-finetune.md) | ![Duration](https://img.shields.io/badge/Duration-14:01-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1sR9fYUE8z)](https://www.bilibili.com/video/BV1sR9fYUE8z) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/FNuEnwrMbas?style=social)](https://youtu.be/FNuEnwrMbas) |\n| 17 | tool-call原理及极简browser-use实现 | [tool-calls](tool-calls/readme.md) | ![Duration](https://img.shields.io/badge/Duration-14:47-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1yUQhYwEJ2)](https://www.bilibili.com/video/BV1yUQhYwEJ2) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/m9GoJVEp-1w?style=social)](https://youtu.be/m9GoJVEp-1w) |\n| 18 | milvus向量数据库 | [milvus](milvus/readme.md) | ![Duration](https://img.shields.io/badge/Duration-28:13-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1T9ZhYnEWW)](https://www.bilibili.com/video/BV1T9ZhYnEWW) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/-qGUeOJJ2eM?style=social)](https://youtu.be/-qGUeOJJ2eM) |\n\n\n\n### 🔋 2. 模块知识专题系列\n\n\u003e 专题系列会以多个视频介绍同一个主题，分P的形式展示，即共用一个video url。\n\n| 序号 | 项目 | 代码文档 | 视频时长 | 视频教程 |\n|------|------|----------|----------|----------|\n| 1 | kaggle 大模型竞赛系列  （🏊更新至01期） | [kaggle](kaggle/getting-started.ipynb) | ![Duration](https://img.shields.io/badge/Duration-25:41-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1vVayeREVe)](https://www.bilibili.com/video/BV1vVayeREVe/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/Mz4V3zinMYI?style=social)](https://youtu.be/Mz4V3zinMYI) |\n| 2 | gradio 使用python构建并分享AI应用（🏊已完结） | [gradio](gradio/README.md) | ![Duration](https://img.shields.io/badge/Duration-70:51-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1TK66YYEvJ)](https://www.bilibili.com/video/BV1TK66YYEvJ/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/sRW_Q0Wzzwo?style=social)](https://youtu.be/sRW_Q0Wzzwo) |\n| 3 | docker 容器化部署（🏊已完结）| [docker](docker/README.md) | ![Duration](https://img.shields.io/badge/Duration-62:59-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1o7y7Y8EZ1)](https://www.bilibili.com/video/BV1o7y7Y8EZ1/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/DeYNR47abG8?style=social)](https://youtu.be/DeYNR47abG8) |\n\n\n\n### 🙌🏻 3. 不着调的AI项目\n\n\u003e 将一些脑洞大开的点子落地成AI项目的不着调专题，应该有点意思吧，哈哈哈。\n\n| 序号 | 项目 | 代码文档 | 视频时长 | 视频教程 |\n|------|------|----------|----------|----------|\n| 1 | D.Va: 基于deepseek优化的端到端多人播客工具 | [d.va](https://github.com/echonoshy/d.va) | ![Duration](https://img.shields.io/badge/Duration-13:42-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1miAYeMEqg)](https://www.bilibili.com/video/BV1gYzEYrEQt/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/XjpNdvl-vvY?style=social)](https://youtu.be/XjpNdvl-vvY) |\n| 2 | 听舒: 换声引擎-用作者的声音读自传 | [tingshu](https://github.com/echonoshy/tingshu) | ![Duration](https://img.shields.io/badge/Duration-4:16-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1miAYeMEqg)](https://www.bilibili.com/video/BV1gYzEYrEQt/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/TdCrbDvICbw?style=social)](https://youtu.be/TdCrbDvICbw) |\n| 3 | 猎空: LLM+微信自动化资讯机器人 | [tracer](https://github.com/echonoshy/tracer) | ![Duration](https://img.shields.io/badge/Duration-15:11-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV15GXQY3Ez3)](https://www.bilibili.com/video/BV15GXQY3Ez3/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/GQqbYRp5GYI?style=social)](https://youtu.be/GQqbYRp5GYI) |\n\n\n\n### 🏖️ 4. 番外篇\n\n\u003e 懒得分类的技术合集。\n\n| 序号 | 项目 | 代码文档 | 视频时长 | 视频教程 |\n|------|------|----------|----------|----------|\n| 1 | B站实现动态转发抽奖 | [bilibili-lottery](dulldrum/bilibili_lottery/bilibili_lottery.md) | ![Duration](https://img.shields.io/badge/Duration-4:40-blue) | [![bilibili](https://img.shields.io/badge/dynamic/json?label=views\u0026style=social\u0026logo=bilibili\u0026query=data.stat.view\u0026url=https%3A%2F%2Fapi.bilibili.com%2Fx%2Fweb-interface%2Fview%3Fbvid%3DBV1zdDpYhEqj)](https://www.bilibili.com/video/BV1zdDpYhEqj/) \u003cbr\u003e [![youtube](https://img.shields.io/youtube/views/Bnb92NG30us?style=social)](https://youtu.be/Bnb92NG30us) |\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fechonoshy%2Fcgft-llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fechonoshy%2Fcgft-llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fechonoshy%2Fcgft-llm/lists"}