{"id":13467430,"url":"https://github.com/Lordog/dive-into-llms","last_synced_at":"2025-03-26T02:31:28.837Z","repository":{"id":232202631,"uuid":"783730789","full_name":"Lordog/dive-into-llms","owner":"Lordog","description":"《动手学大模型Dive into LLMs》系列编程实践教程","archived":false,"fork":false,"pushed_at":"2024-09-20T04:48:04.000Z","size":82349,"stargazers_count":4665,"open_issues_count":2,"forks_count":432,"subscribers_count":28,"default_branch":"main","last_synced_at":"2025-03-25T07:13:04.521Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://sjtullm.gitbook.io/dive-into-llms","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Lordog.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-04-08T13:11:40.000Z","updated_at":"2025-03-25T06:26:33.000Z","dependencies_parsed_at":"2024-10-29T20:40:37.516Z","dependency_job_id":null,"html_url":"https://github.com/Lordog/dive-into-llms","commit_stats":null,"previous_names":["lordog/llm-tutorial-by-hand","lordog/dive-into-llms"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lordog%2Fdive-into-llms","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lordog%2Fdive-into-llms/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lordog%2Fdive-into-llms/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Lordog%2Fdive-into-llms/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Lordog","download_url":"https://codeload.github.com/Lordog/dive-into-llms/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245576529,"owners_count":20638125,"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":"2024-07-31T15:00:56.271Z","updated_at":"2025-03-26T02:31:28.817Z","avatar_url":"https://github.com/Lordog.png","language":null,"funding_links":[],"categories":["Jupyter Notebook","largemodel","A01_文本生成_文本对话","书籍 Book","学习资源","Repos"],"sub_categories":["大语言对话模型及数据","学习项目"],"readme":"\u003cp align=\"center\"\u003e\n\u003ch1 align=\"center\"\u003e \u003cimg src=\"./pics/icon/ai.png\" width=\"30\" /\u003e《动手学大模型》系列编程实践教程\u003c/h1\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \t\u003ca href=\"https://img.shields.io/badge/version-v0.1.0-blue\"\u003e\n      \u003cimg alt=\"version\" src=\"https://img.shields.io/badge/version-v0.1.0-blue?color=FF8000?color=009922\" /\u003e\n    \u003c/a\u003e\n  \u003ca \u003e\n       \u003cimg alt=\"Status-building\" src=\"https://img.shields.io/badge/Status-building-blue\" /\u003e\n  \t\u003c/a\u003e\n  \u003ca \u003e\n       \u003cimg alt=\"PRs-Welcome\" src=\"https://img.shields.io/badge/PRs-Welcome-red\" /\u003e\n  \t\u003c/a\u003e\n   \t\u003ca href=\"https://github.com/Lordog/dive-into-llms/stargazers\"\u003e\n       \u003cimg alt=\"stars\" src=\"https://img.shields.io/github/stars/Lordog/dive-into-llms\" /\u003e\n  \t\u003c/a\u003e\n  \t\u003ca href=\"https://github.com/Lordog/dive-into-llms/network/members\"\u003e\n       \u003cimg alt=\"FORK\" src=\"https://img.shields.io/github/forks/Lordog/dive-into-llms?color=FF8000\" /\u003e\n  \t\u003c/a\u003e\n    \u003ca href=\"https://github.com/Lordog/dive-into-llms/issues\"\u003e\n      \u003cimg alt=\"Issues\" src=\"https://img.shields.io/github/issues/Lordog/dive-into-llms?color=0088ff\"/\u003e\n    \u003c/a\u003e\n    \u003cbr /\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#项目动机\"\u003e项目动机\u003c/a\u003e/\n  \u003ca href=\"#教程目录\"\u003e教程目录\u003c/a\u003e/\n  \u003ca href=\"#贡献者列表\"\u003e贡献者列表\u003c/a\u003e\n\u003c/p\u003e\n\u003c/div\u003e\n\n\n## \u003cimg src=\"./pics/icon/motivation.png\" width=\"25\" /\u003e项目动机\n\n《动手学大模型》系列编程实践教程，由上海交通大学2024年春季《人工智能安全技术》课程（NIS3353）讲义拓展而来（教师：[张倬胜](https://bcmi.sjtu.edu.cn/home/zhangzs/)），旨在提供大模型相关的入门编程参考。通过简单实践，帮助同学快速入门大模型，更好地开展课程设计或学术研究。\n\n## \u003cimg src=\"./pics/icon/catalogue.png\" width=\"25\" /\u003e教程目录\n\n| 教程内容           | 简介                                                         | 地址                                                         |\n| ------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |\n| 微调与部署         | 预训练模型微调与部署指南：想提升预训练模型在指定任务上的性能？让我们选择合适的预训练模型，在特定任务上进行微调，并将微调后的模型部署成方便使用的Demo！ | [[Slides](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter1/dive-tuning.pdf)] [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter1/README.md)] |\n| 提示学习与思维链   | 大模型的API调用与推理指南：“AI在线求鼓励？大模型对一些问题的回答令人大跌眼镜，但它可能只是想要一句「鼓励」” | [[Slides](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter2/dive-prompting.pdf)] [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter2/README.md)] |\n| 知识编辑           | 语言模型的编辑方法和工具：想操控语言模型在对指定知识的记忆？让我们选择合适的编辑方法，对特定知识进行编辑，并将对编辑后的模型进行验证！ | [[Slides](https://github.com/Lordog/dive-into-llms/blob/main/documents/chapter3/dive_edit_0410.pdf)] [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter3/README.md)] |\n| 模型水印           | 语言模型的文本水印：在语言模型生成的内容中嵌入人类不可见的水印 | [[Slides](https://github.com/Lordog/dive-into-llms/blob/main/documents/chapter4/watermark.pdf)] [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter4/README.md)] |\n| 越狱攻击           | 想要得到更好的安全，要先从学会攻击开始。让我们了解越狱攻击如何撬开大模型的嘴！                                                          | [[Slides](https://github.com/Lordog/dive-into-llms/blob/main/documents/chapter5/dive-Jailbreak.pdf)]  [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter5/README.md)]                                                        |\n| 多模态模型         | 作为能够更充分模拟真实世界的多模态大语言模型，其如何实现更强大的多模态理解和生成能力？多模态大语言模型是否能够帮助实现AGI？  | [[Slides](https://github.com/Lordog/dive-into-llms/blob/main/documents/chapter6/mllms.pdf)]  [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter6/README.md)]   |\n| 大模型智能体与安全 | 大模型智能体迈向了未来操作系统之旅。然而，大模型在开放智能体场景中能意识到风险威胁吗？ | [[Slides](https://github.com/Lordog/dive-into-llms/blob/main/documents/chapter7/agent.pdf)] [[Tutorial](https://github.com/Lordog/dive-into-llms/tree/main/documents/chapter7/README.md)] |\n\n### \u003cimg src=\"./pics/icon/notes.png\" width=\"25\" /\u003e免责声明\n\n本教程所有内容仅仅来自于贡献者的个人经验、互联网数据、日常科研工作中的相关积累。所有技巧仅供参考，不保证百分百正确。若有任何问题，欢迎提交 Issue 或 PR。另本项目所用徽章来自互联网，如侵犯了您的图片版权请联系我们删除，谢谢。\n\n### \u003cimg src=\"./pics/icon/resource.png\" width=\"25\" /\u003e欢迎贡献\n\n本教程目前是一个正在进行中的项目，如有疏漏在所难免，欢迎任何的PR及issue讨论。\n\n## \u003cimg src=\"./pics/icon/heart.png\" width=\"25\" /\u003e贡献者列表\n\n感谢以下老师和同学对本项目的支持与贡献：\n\n上海交通大学 [袁童鑫](https://github.com/Lordog)\n\n上海交通大学 [马欣贝](https://scholar.google.com/citations?user=LpUi3EgAAAAJ\u0026hl=zh-CN\u0026oi=ao)\n\n上海交通大学 [何志威](https://zwhe99.github.io)\n\n上海交通大学 杜巍\n\n上海交通大学 [赵皓东](https://dongdongzhaoup.github.io/)\n\n新加坡国立大学 [费豪](http://haofei.vip/)\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=Lordog/dive-into-llms\u0026type=Date)](https://star-history.com/#Lordog/dive-into-llms\u0026Date)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLordog%2Fdive-into-llms","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FLordog%2Fdive-into-llms","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FLordog%2Fdive-into-llms/lists"}