启动器.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e5c5a211-2ccd-4341-af10-ac546484b91f",
   "metadata": {
    "tags": []
   },
   "source": [
    "## 项目介绍\n",
    "- 原项目地址：\n",
    "    - https://github.com/ollama/ollama\n",
    "    - https://github.com/open-webui/open-webui\n",
    "- ollama-webui：一款带有webui的大模型聊天工具\n",
    "## 使用说明\n",
    "\n",
    "- 启动和重启 Notebook 点上方工具栏中的「重启并运行所有单元格」，出现`Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit)`就成功，可以开启页面了\n",
    "- 通过以下方式开启页面：\n",
    "    - 控制台打开「自定义服务」了，访问自定义服务端口号设置为8080\n",
    "- 首次使用：**注意：注册信息只存放在容器内部，不会上传互联网，请放心使用**\n",
    "    1. 点击`注册`<br>\n",
    "       <img src=\"./assets/注册.png\" style=\"width:30%;\">\n",
    "    2. 点击`创建账号`<br>\n",
    "        <img src=\"./assets/创建账号.png\" style=\"width:30%;\">\n",
    "- 管理员相关：\n",
    "    - 账号：用户名：`ollama`，邮箱：`ollama@ollama.cn`，密码：`pass`\n",
    "    - 管理员可修改新用户注册、默认用户角色等信息，可在`管理员面板`打开<br>\n",
    "      <img src=\"./assets/管理员面板.png\" style=\"width:80%;\">\n",
    "    - 也可对注册用户进行删除等操作，可在`仪表盘`打开<br>\n",
    "        <img src=\"./assets/仪表盘.png\" style=\"width:80%;\">\n",
    "\n",
    "- 下载模型：\n",
    "    - 方法1:在页面搜索下载，模型会自动从Ollama.com拉取，支持模型见方法2中的模型<br>\n",
    "    <img src=\"./assets/搜索下载模型.png\" style=\"width:80%;\">\n",
    "    - 方法2:新建启动页，打开终端输入`Download`中命令，然后刷新通过「自定义服务」的页面即可使用\n",
    "| Model              | Parameters | Size  | Download                       |\n",
    "| ------------------ | ---------- | ----- | ------------------------------ |\n",
    "| Llama 3.1          | 8B         | 4.7GB | `ollama pull llama3.1`          |\n",
    "| Llama 3.1          | 70B        | 40GB  | `ollama pull llama3.1:70b`      |\n",
    "| Llama 3.1          | 405B       | 231GB | `ollama pull llama3.1:405b`     |\n",
    "| Phi 3 Mini         | 3.8B       | 2.3GB | `ollama pull phi3`              |\n",
    "| Phi 3 Medium       | 14B        | 7.9GB | `ollama pull phi3:medium`       |\n",
    "| Gemma 2            | 2B         | 1.6GB | `ollama pull gemma2:2b`         |\n",
    "| Gemma 2            | 9B         | 5.5GB | `ollama pull gemma2`            |\n",
    "| Gemma 2            | 27B        | 16GB  | `ollama pull gemma2:27b`        |\n",
    "| Mistral            | 7B         | 4.1GB | `ollama pull mistral`           |\n",
    "| Moondream 2        | 1.4B       | 829MB | `ollama pull moondream`         |\n",
    "| Neural Chat        | 7B         | 4.1GB | `ollama pull neural-chat`       |\n",
    "| Starling           | 7B         | 4.1GB | `ollama pull starling-lm`       |\n",
    "| Code Llama         | 7B         | 3.8GB | `ollama pull codellama`         |\n",
    "| Llama 2 Uncensored | 7B         | 3.8GB | `ollama pull llama2-uncensored` |\n",
    "| LLaVA              | 7B         | 4.5GB | `ollama pull llava`             |\n",
    "| Solar              | 10.7B      | 6.1GB | `ollama pull solar`             |\n",
    "- 其他高级操作参考：\n",
    "    - https://github.com/ollama/ollama\n",
    "    - https://github.com/open-webui/open-webui\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9e81ae9d-3a34-43a0-943a-ff5e9d6ce961",
   "metadata": {},
   "outputs": [],
   "source": [
    "# 启动\n",
    "!sh start.sh"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9c881a9d-351b-4d76-b1ef-7b0e2f1910d6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}