{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a25f3d36-e14f-4afd-8926-32748a42e1d1",
   "metadata": {},
   "source": [
    "# 1 大模型运行环境简介\n",
    "\n",
    "\n",
    "建议直接使用autodl，google colab等环境\n",
    "\n",
    "显卡：4090或者4090d\n",
    "\n",
    "内存：32G至少\n",
    "\n",
    "torch>=2.3.0\n",
    "\n",
    "具体可以参考：https://zhuanlan.zhihu.com/p/13479003076\n",
    "\n",
    "pip安装下面的基本transformer环境即可："
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cdeae2e5-2a39-4370-a5ec-47780f8fa76a",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install transformers sentencepiece google protobuf deepspeed peft datasets "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a355a6e6-62fc-4b8f-ba35-b9c2f0ef48c8",
   "metadata": {},
   "source": [
    "如要运行deepspeed，一般使用一机多卡即可，本教程一般不会涉及需要多机多卡的案例\n",
    "\n",
    "\n",
    "推荐的gpu主机：\n",
    "* autodl.com, 国内的 \n",
    "* vast.ai, 海外的\n",
    "\n",
    "主流云平台gpu一般都特别贵，也不允许运行4090等显卡。"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4ee0674c-f001-453f-b0b0-7e3b25309040",
   "metadata": {},
   "source": [
    "另外，建议把jupyter的注释打开，这样非常方便学习\n",
    "\n",
    "<img src=\"img/zhushi.png\" alt=\"示例图片\" width=\"500px\" />"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "444adc87-78c8-4209-8260-0c5c4a668ea0",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "# 设置环境变量, autodl专区 其他idc\n",
    "os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'\n",
    "\n",
    "# 打印环境变量以确认设置成功\n",
    "print(os.environ.get('HF_ENDPOINT'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "06d9dc67-dbd4-4d37-bbdb-ccf59c8fdbf9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import subprocess\n",
    "import os\n",
    "# 设置环境变量, autodl一般区域\n",
    "result = subprocess.run('bash -c \"source /etc/network_turbo && env | grep proxy\"', shell=True, capture_output=True, text=True)\n",
    "output = result.stdout\n",
    "for line in output.splitlines():\n",
    "    if '=' in line:\n",
    "        var, value = line.split('=', 1)\n",
    "        os.environ[var] = value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2168e365-8254-4063-98bd-27afdbdb2f32",
   "metadata": {},
   "outputs": [],
   "source": [
    "#lfs 支持\n",
    "!apt-get update\n",
    "\n",
    "!apt-get install git-lfs\n",
    "\n",
    "!git lfs install"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}