Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
how_to_make_LLM
Published:
一、简介
主要分为以下五部分：
1. 需求和技术
- 企业对于大模型的不同类型个性化需求
- SFT（有监督微调）、RLHF（强化学习）、RAG（检索增强生成） -关注：基本概念；分别解决什么问题；如何根据需求选择；
- 微调部分详细介绍：
- 微调算法的分类
- **LoRA 微调算法
- 微调常见实现框架
2. 整体步骤说明
- 在 Linux 系统上微调一个大模型、部署模型、暴露 API 给 web 后端调用，本机前端展示全过程
3. 模型微调
- 框架: LLama-Factory (国产最热门的微调框架)
- 算法: **LoRA (最著名的部分参数微调算法）
- 基座模型：DeepSeek-R1-Distill-Qwen-1.5B -蒸馏技术通常用于通过将大模型（教师模型）的知识转移到小模型（学生模型）中，使得小模型能够在尽量保持性能的同时，显著减少模型的参数量和计算需求。
4. 模型部署和暴露接口
- 框架：FastAPI（一个基于 python 的 web 框架）
5. web后端调用
- 通过 HTTP 请求交互即可（ Demo 前后端代码都在视频简介）
dailyResource
Published:
这篇博客介绍了一些日常收集整理资料。
how_to_use_remoteSSH
Published:
这篇博客介绍了如何在Ubuntu系统和路由器的局域网连接中，配置路由器的端口转发服务。
how_to_change_githubStyle
Published:
这篇博客介绍了如何修改github的样式，包括修改主题、字体、背景等。
how_to_learn_graphNetwork
Published:
这篇博客介绍了图神经网络（GNNs）。
how_to_ScatterPlots_onMap
Published:
这篇博客撰写了编写相应的代码，将经纬度信息以图形化的方式呈现出来。
what_Torchversion_install
Published:
这篇博客介绍了如何安装和使用 PyTorch 最新版本，同时提供了旧版本的安装指南，帮助用户根据需求快速开始机器学习开发。
how_to_do_ScientificResearchDrawings
Published:
这篇博客主要存储一些latex的语法工具链接。
how_to_make_GitubwithJekyll_in_windows
Published:
这篇博客介绍了如何在gitubPage上的学术网站（个人学术页面）。
portfolio
Portfolio item number 2
Short description of portfolio item number 2 
publications
Paper Title Number 1
Published in Journal 1, 2009
This paper is about the number 1. The number 2 is left for future work.
Recommended citation: Your Name, You. (2009). "Paper Title Number 1." Journal 1. 1(1).
Download Paper | Download Slides
Paper Title Number 2
Published in Journal 1, 2010
This paper is about the number 2. The number 3 is left for future work.
Recommended citation: Your Name, You. (2010). "Paper Title Number 2." Journal 1. 1(2).
Download Paper | Download Slides
Paper Title Number 3
Published in Journal 1, 2015
This paper is about the number 3. The number 4 is left for future work.
Recommended citation: Your Name, You. (2015). "Paper Title Number 3." Journal 1. 1(3).
Download Paper | Download Slides
Paper Title Number 4
Published in GitHub Journal of Bugs, 2024
This paper is about fixing template issue #693.
Recommended citation: Your Name, You. (2024). "Paper Title Number 3." GitHub Journal of Bugs. 1(3).
Download Paper
talks
Easy-to-understand DTW algorithm
Published:
DTW stands for Dynamic Time Warping, which is an algorithm used for measuring the similarity between time series data. “Welcome to my insightful session on the Dynamic Time Warping (DTW) algorithm! In this video, we’ll delve into the world of time series analysis and explore how DTW can be a game-changer. Whether you’re a beginner or have some experience, we’ve designed this tutorial to be easy-to-understand and highly informative. Join us as we unravel the mysteries of DTW, its applications, and how you can leverage it for your data analysis needs. Get ready to transform your understanding of time series data with our step-by-step guide to the DTW algorithm!”
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Heading 1
Heading 2
Heading 3
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.