LLM@本地大语言模型@Gemma的安装与使用@dockerDesktop的安装和启动

文章目录

准备

  • 在windows环境下操作,可能要代理改善下载体验

refs

ollama

安装过程

  • 安装完ollama,检查是否正确安装:

    bash 复制代码
    PS BAT [10:21:12 AM] [C:\Users\cxxu\Desktop]
    [🔋 100%] MEM:73.71% [5.79/7.85] GB |ollama --version
    ollama version is 0.1.27
  • 开始安装模型(这里使用的电脑没有GPU,所以选择用cpu就可以运行的2b模型(20亿参数),对内存要求也不高,我这里只有约8GB内存)

    bash 复制代码
    PS BAT [10:21:17 AM] [C:\Users\cxxu\Desktop]
    [🔋 100%] MEM:71.47% [5.61/7.85] GB |ollama run gemma:2b
    pulling manifest
    pulling c1864a5eb193...   1% ▕                                                        ▏  14 MB/1.7 GB  1.5 MB/s   18m1s
    
    PS BAT [10:28:04 AM] [C:\Users\cxxu\Desktop]
    [🔋 100%] MEM:48.33% [3.79/7.85] GB |ollama run gemma:2b
    pulling manifest
    pulling c1864a5eb193... 100% ▕████████████████████████████████████████████████████████▏ 1.7 GB
    pulling 097a36493f71... 100% ▕████████████████████████████████████████████████████████▏ 8.4 KB
    pulling 109037bec39c... 100% ▕████████████████████████████████████████████████████████▏  136 B
    pulling 22a838ceb7fb... 100% ▕████████████████████████████████████████████████████████▏   84 B
    pulling 887433b89a90... 100% ▕████████████████████████████████████████████████████████▏  483 B
    verifying sha256 digest
    writing manifest
    removing any unused layers
    success
    • 模型下载:我这里国内网络下载的挺快的,但是后面5%很慢,不知道为什么(有的可能会遇到下载不下来的情况,考虑切换网络环境或时间段重试,或者需要全局代理(you know))
  • 简单聊两句

    bash 复制代码
    >>> hello!
    Hello! 👋  It's nice to hear from you. How can I help you today? 😊
    
    >>> introduce yourself please😁
    Hey there! It's great to meet you as well! I'm a language AI, and I'm here to assist you with any questions or
    tasks you may have. How can I help you today?
    >>> how do you think about google
    Google is an American multinational technology company that specializes in search engines, software, and other
    services. They are one of the most valuable companies in the world, and their search engine is the most widely
    used in the world.
    
    What do you think about Google? Is it a good company to work for? What are your thoughts on their products and
    services?
    
    >>> replay it in Chinese anagin!
    谷歌是美國著名的科技公司,致力於搜尋引擎、軟體和其他服務。他們是世界上最具價值的公司之一,他們的搜尋引擎是世界最使用的之一。
    
    你對谷歌有什麼看法?谷歌是一個好的公司嗎?你對他們的產品和服務有什麼看法?

2b模型的效果小结👺

  • 2b模型不给力,至少中文方面是这样的,不知道7b的如何

bash 复制代码
>>> 鲁迅和周树人的关系?
鲁迅和周树人之间存在着深厚的友情和敬意之情。鲁迅是周树人 的好友和老师,两人在文学创作、政治活动和社会发展鲁迅和周 树人之间存在着深厚的友情和敬意之情。鲁迅是周树人的好友和 老师,两人在文学创作、政治活动和社会发展方面有着深远的影 响力。

**鲁迅对周树人的影响:**

* 鲁迅是周树人的文学老师,他对周树人的写作技巧和精神追求 给予了指导。
* 鲁迅曾写了一首诗,以表彰周树人的对中国文化的贡献,称为"周树人颂"。
  • 让它写一段快速排序也是错误的

ollama的进一步使用

帮助文档

bash 复制代码
PS>ollama --help
Large language model runner

Usage:
  ollama [flags]
  ollama [command]

Available Commands:
  serve       Start ollama
  create      Create a model from a Modelfile
  show        Show information for a model
  run         Run a model
  pull        Pull a model from a registry
  push        Push a model to a registry
  list        List models
  cp          Copy a model
  rm          Remove a model
  help        Help about any command

Flags:
  -h, --help      help for ollama
  -v, --version   Show version information

Use "ollama [command] --help" for more information about a command.

查看ollama安装了哪些模型

bash 复制代码
PS>ollama list
NAME            ID              SIZE    MODIFIED
gemma:2b        b50d6c999e59    1.7 GB  17 minutes ago

使用皮肤来使聊天更易用

使用Chatbot UI皮肤

  • 这里以chatbot为例

安装docker👺

  • 使用docker方案安装UI:

  • 安装dockerd的过程启动安装界面比较慢,耐心等待,不要重复点击

    • docker版本更新:如果要安装新版的docker,直接安装可能会被阻止(旧版本的进程可能不容易杀死)
    • 建议更新前注销当前账户(登出windows),或者重启后安装
  • 安装或更新完毕,会要求重启电脑(对于初次安装使用者,先不要重启,看下一节)

启动docker

  • 如果安装时勾选了wsl2代替hyperv,那么重启电脑前执行wsl --update
  • 即重启前请执行wsl --update,否则即便重启后也可能无法启动docker
  • 执行完上述命令后重启
  • 然后以管理员权限运行docker,通常来讲就可成功启动docker

载入和退出docker

  • 进入docker和退出docker都挺耗时的,需要耐心一些(但是一般也不会超过2分钟,否则就可能是出问题了),毕竟是虚拟机操作

chatbot 网页版皮肤

  • 国内直接安装是不容易下载下来(很慢),用代理的话可以快点,打断后需要重新下载一遍

    bash 复制代码
    PS BAT [12:05:45 PM] [C:\Users\cxxu\Desktop]
    [🔋 100%] MEM:73.05% [5.73/7.85] GB |docker run -p 3000:3000 ghcr.io/ivanfioravanti/chatbot-ollama:main
    Unable to find image 'ghcr.io/ivanfioravanti/chatbot-ollama:main' locally
    main: Pulling from ivanfioravanti/chatbot-ollama
    4abcf2066143: Pull complete
    2f6d6b553e5a: Pull complete
    c6a5f30c1979: Pull complete
    0fff72987922: Pull complete
    eb03cd48595f: Pull complete
    80fa45e7c128: Pull complete
    f3a6b16fbbb9: Pull complete
    ba832799bc4f: Pull complete
    23fd0e505f52: Pull complete
    45892a5fb863: Pull complete
    e5e1e83df1a2: Pull complete
    Digest: sha256:a6bebee38b0359f092eca6cd6bf6cf49e36b9b0e4e28c8376e27d61c96a81e63
    Status: Downloaded newer image for ghcr.io/ivanfioravanti/chatbot-ollama:main
    
    > [email protected] start
    > next start
    
       ▲ Next.js 14.1.0
       - Local:        http://localhost:3000
    
     ✓ Ready in 1610ms
  • 可能遇到的报错

    bash 复制代码
    PS BAT [12:05:27 PM] [C:\Users\cxxu\Desktop]
    [🔋 100%] MEM:72.28% [5.67/7.85] GB |docker run -p 3000:3000 ghcr.io/ivanfioravanti/chatbot-ollama:main
    
    Unable to find image 'ghcr.io/ivanfioravanti/chatbot-ollama:main' locally
    docker: Error response from daemon: Head "https://ghcr.io/v2/ivanfioravanti/chatbot-ollama/manifests/main": net/http: TLS handshake timeout.
    See 'docker run --help'.
    • 重试一两次即可,如果仍然不成功,可能是docker没安装好或网络不行

使用命令行聊天

  • 比起使用皮肤聊天,命令行方式少占用点资源,会输出顺畅一些

  • 使用cmd可能要比powershell好点(特别是powershell安装了皮肤,容易导致显示问题)

  • 使用ollama run gemma:2b启动模型,需要若干秒的时间(2b模型太拉了,别较真)

bash 复制代码
PS>ollama run gemma:2b
>>> 陆地上哪种生物跑 得最快
陆地上最大的速度是**松鼠**跑得最快,可以达到**90公里每小时**。

>>> what's the fastest fish in the sea?
最快的鱼是**热带鱼**,可以达到**60公里每小时**。

>>> the area of China
中国是世界上拥有最大生物多样性的国家,也是世界上速度最大生物的产地。

**松鼠**是世界上速度最快的动物,可以达到**90公里每小时**。
**热带鱼**是世界上速度第二快的鱼,可以达到**60公里每小时**。

小结👺

  • 低配电脑还是不要本地大模型了,配置不够,对话体验相当差(慢且乱),还是老老实实用在线大模型吧

  • 很离谱,下面的对话🤣

相关推荐
憨憨睡不醒啊2 小时前
如何让LLM智能体开发助力求职之路——构建属于你的智能体开发知识体系📚📚📚
面试·程序员·llm
柯南二号3 小时前
深入理解 Agent 与 LLM 的区别:从智能体到语言模型
人工智能·机器学习·llm·agent
Q同学5 小时前
TORL:工具集成强化学习,让大语言模型学会用代码解题
深度学习·神经网络·llm
人肉推土机9 小时前
AI Agent 架构设计:ReAct 与 Self-Ask 模式对比与分析
人工智能·大模型·llm·agent
洗澡水加冰9 小时前
n8n搭建多阶段交互式工作流
后端·llm
中杯可乐多加冰13 小时前
【解决方案-RAGFlow】RAGFlow显示Task is queued、 Microsoft Visual C++ 14.0 or greater is required.
人工智能·大模型·llm·rag·ragflow·deepseek
Baihai IDP1 天前
“一代更比一代强”:现代 RAG 架构的演进之路
ai·llm·rag·genai·白海科技·检索增强生成
Q同学1 天前
Qwen3开源最新Embedding模型
深度学习·神经网络·llm
用户84913717547161 天前
🚀 为什么猫和狗更像?用“向量思维”教会 AI 懂语义!
人工智能·llm
AI大模型知识1 天前
Qwen3+Ollama本地部署MCP初体验
人工智能·llm