02_prompt/02_llama2_chain_of_thought_huggingface.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f6011cb7-fd15-4379-be46-02b4ffdb3fe5",
   "metadata": {},
   "source": [
    "# Tested on a g5.4xlarge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d7864435-3f09-4834-8725-5e938c8303ae",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: torch==2.0.1 in /opt/conda/lib/python3.10/site-packages (2.0.1)\n",
      "Collecting transformers==4.33.0\n",
      "  Obtaining dependency information for transformers==4.33.0 from https://files.pythonhosted.org/packages/e1/9d/4d9fe5c3b820db10773392ac5f4a0c8dab668f70b245ce2ce09785166128/transformers-4.33.0-py3-none-any.whl.metadata\n",
      "  Using cached transformers-4.33.0-py3-none-any.whl.metadata (119 kB)\n",
      "Requirement already satisfied: sentencepiece==0.1.99 in /opt/conda/lib/python3.10/site-packages (0.1.99)\n",
      "Requirement already satisfied: accelerate==0.22.0 in /opt/conda/lib/python3.10/site-packages (0.22.0)\n",
      "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (3.6.0)\n",
      "Requirement already satisfied: typing-extensions in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (4.3.0)\n",
      "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (1.10.1)\n",
      "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (2.8.4)\n",
      "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (3.1.2)\n",
      "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.7.99)\n",
      "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.7.99)\n",
      "Requirement already satisfied: nvidia-cuda-cupti-cu11==11.7.101 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.7.101)\n",
      "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (8.5.0.96)\n",
      "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.10.3.66)\n",
      "Requirement already satisfied: nvidia-cufft-cu11==10.9.0.58 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (10.9.0.58)\n",
      "Requirement already satisfied: nvidia-curand-cu11==10.2.10.91 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (10.2.10.91)\n",
      "Requirement already satisfied: nvidia-cusolver-cu11==11.4.0.1 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.4.0.1)\n",
      "Requirement already satisfied: nvidia-cusparse-cu11==11.7.4.91 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.7.4.91)\n",
      "Requirement already satisfied: nvidia-nccl-cu11==2.14.3 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (2.14.3)\n",
      "Requirement already satisfied: nvidia-nvtx-cu11==11.7.91 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (11.7.91)\n",
      "Requirement already satisfied: triton==2.0.0 in /opt/conda/lib/python3.10/site-packages (from torch==2.0.1) (2.0.0)\n",
      "Requirement already satisfied: huggingface-hub<1.0,>=0.15.1 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (0.17.3)\n",
      "Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (1.26.0)\n",
      "Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (21.3)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages/PyYAML-6.0-py3.10-linux-x86_64.egg (from transformers==4.33.0) (6.0)\n",
      "Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (2022.7.9)\n",
      "Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (2.31.0)\n",
      "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers==4.33.0)\n",
      "  Using cached tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n",
      "Requirement already satisfied: safetensors>=0.3.1 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (0.4.0)\n",
      "Requirement already satisfied: tqdm>=4.27 in /opt/conda/lib/python3.10/site-packages (from transformers==4.33.0) (4.64.1)\n",
      "Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from accelerate==0.22.0) (5.9.0)\n",
      "Requirement already satisfied: setuptools in /opt/conda/lib/python3.10/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch==2.0.1) (68.2.2)\n",
      "Requirement already satisfied: wheel in /opt/conda/lib/python3.10/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch==2.0.1) (0.41.2)\n",
      "Requirement already satisfied: cmake in /opt/conda/lib/python3.10/site-packages (from triton==2.0.0->torch==2.0.1) (3.27.7)\n",
      "Requirement already satisfied: lit in /opt/conda/lib/python3.10/site-packages (from triton==2.0.0->torch==2.0.1) (17.0.3)\n",
      "Requirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from huggingface-hub<1.0,>=0.15.1->transformers==4.33.0) (2023.6.0)\n",
      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging>=20.0->transformers==4.33.0) (3.0.9)\n",
      "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch==2.0.1) (2.1.3)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.33.0) (2.0.4)\n",
      "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.33.0) (3.3)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.33.0) (2.0.6)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->transformers==4.33.0) (2023.7.22)\n",
      "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch==2.0.1) (1.3.0)\n",
      "Using cached transformers-4.33.0-py3-none-any.whl (7.6 MB)\n",
      "Installing collected packages: tokenizers, transformers\n",
      "  Attempting uninstall: tokenizers\n",
      "    Found existing installation: tokenizers 0.14.1\n",
      "    Uninstalling tokenizers-0.14.1:\n",
      "      Successfully uninstalled tokenizers-0.14.1\n",
      "  Attempting uninstall: transformers\n",
      "    Found existing installation: transformers 4.34.1\n",
      "    Uninstalling transformers-4.34.1:\n",
      "      Successfully uninstalled transformers-4.34.1\n",
      "Successfully installed tokenizers-0.13.3 transformers-4.33.0\n",
      "\u001b[33mWARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv\u001b[0m\u001b[33m\n",
      "\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3\u001b[0m\n",
      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install -U torch==2.0.1 \\\n",
    "  transformers==4.33.0 \\\n",
    "  sentencepiece==0.1.99 \\\n",
    "  accelerate==0.22.0 # needed for low_cpu_mem_usage parameter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "b48c0687-ade4-4e7e-812a-99f0cfeca9c4",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import torch\n",
    "from transformers import LlamaTokenizer\n",
    "\n",
    "model_checkpoint = \"NousResearch/Llama-2-13b-chat-hf\"\n",
    "tokenizer = LlamaTokenizer.from_pretrained(model_checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "4eeaafdb-8482-4491-bba2-5b3b389813c3",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# based on https://github.com/viniciusarruda/llama-cpp-chat-completion-wrapper/blob/1c9e29b70b1aaa7133d3c7d7b59a92d840e92e6d/llama_cpp_chat_completion_wrapper.py\n",
    "\n",
    "from typing import List\n",
    "from typing import Literal\n",
    "from typing import TypedDict\n",
    "\n",
    "from transformers import PreTrainedTokenizer\n",
    "\n",
    "Role = Literal[\"system\", \"user\", \"assistant\"]\n",
    "\n",
    "class Message(TypedDict):\n",
    "    role: Role\n",
    "    content: str\n",
    "\n",
    "MessageList = List[Message]\n",
    "\n",
    "BEGIN_INST, END_INST = \"[INST] \", \" [/INST] \"\n",
    "BEGIN_SYS, END_SYS = \"<<SYS>>\\n\", \"\\n<</SYS>>\\n\\n\"\n",
    "\n",
    "def convert_list_of_message_lists_to_input_prompt(list_of_message_lists: List[MessageList], tokenizer: PreTrainedTokenizer) -> List[str]:\n",
    "    input_prompts: List[str] = []\n",
    "    print(type(list_of_message_lists))\n",
    "    print(type(list_of_message_lists[0]))    \n",
    "    for message_list in list_of_message_lists:\n",
    "        if message_list[0][\"role\"] == \"system\":\n",
    "            content = \"\".join([BEGIN_SYS, message_list[0][\"content\"], END_SYS, message_list[1][\"content\"]])\n",
    "            message_list = [{\"role\": message_list[1][\"role\"], \"content\": content}] + message_list[2:]\n",
    "\n",
    "        if not (\n",
    "            all([msg[\"role\"] == \"user\" for msg in message_list[::2]])\n",
    "            and all([msg[\"role\"] == \"assistant\" for msg in message_list[1::2]])\n",
    "        ):\n",
    "            raise ValueError(\n",
    "                \"Format must be in this order: 'system', 'user', 'assistant' roles.\\nAfter that, you can alternate between user and assistant multiple times\"\n",
    "            )\n",
    "\n",
    "        eos = tokenizer.eos_token\n",
    "        bos = tokenizer.bos_token\n",
    "        input_prompt = \"\".join(\n",
    "            [\n",
    "                \"\".join([bos, BEGIN_INST, (prompt[\"content\"]).strip(), END_INST, (answer[\"content\"]).strip(), eos])\n",
    "                for prompt, answer in zip(message_list[::2], message_list[1::2])\n",
    "            ]\n",
    "        )\n",
    "\n",
    "        if message_list[-1][\"role\"] != \"user\":\n",
    "            raise ValueError(f\"Last message must be from user role. Instead, you sent from {message_list[-1]['role']} role\")\n",
    "\n",
    "        input_prompt += \"\".join([bos, BEGIN_INST, (message_list[-1][\"content\"]).strip(), END_INST])\n",
    "\n",
    "        input_prompts.append(input_prompt)\n",
    "\n",
    "    return input_prompts"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1cf0ab54-bbad-42b9-a2ba-17cf4e28fbee",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'role': 'system', 'content': ''}\n",
      "<class 'list'>\n",
      "<class 'list'>\n",
      "['<s>[INST] <<SYS>>\\n\\n<</SYS>>\\n\\n\\nQUESTION: Ducks need to eat 3.5 pounds of insects each week to survive. \\nIf there is a flock of ten ducks, how many pounds of insects do they need per day?\\nANSWER: Ducks need 3.5 pounds of insects each week. If there is a flock of 10 ducks, then they need 3.5 x 10 = 35 pounds of insects each week. If they need 35 pounds of insects each week, then they need 35 / 7 = 5 pounds of insects each day. The answer is 5. \\n\\nQUESTION: It takes Matthew 3 minutes to dig a small hole for shrubs and 10 minutes to dig a large hole for trees.\\nHow many hours will it take him to dig 30 small holes and 15 large holes?\\nANSWER: It takes Matthew 3 minutes to dig a small hole and 10 minutes to dig a large hole. So, it takes Matthew 3 x 30 = 90 minutes to dig 30 small holes. It takes Matthew 10 x 15 = 150 minutes to dig 15 large holes. So, it takes Matthew 90 + 150 = 240 minutes to dig 30 small holes and 15 large holes. 240 minutes is 4 hours. The answer is 4 hours. \\n\\nQUESTION: I have 10 liters of orange drink that are two-thirds water and I wish to add it to 15 liters of pineapple drink that is three-fifths water. \\nBut as I pour it, I spill one liter of the orange drink. How much water is in the remaining 24 liters?\\nANSWER: [/INST] ']\n"
     ]
    }
   ],
   "source": [
    "system_message = Message()\n",
    "system_message[\"role\"] = \"system\"\n",
    "system_message[\"content\"] = \"\"\n",
    "print(system_message)\n",
    "\n",
    "user_message = Message()\n",
    "user_message[\"role\"] = \"user\"\n",
    "user_message[\"content\"] = \"\"\"\n",
    "QUESTION: Ducks need to eat 3.5 pounds of insects each week to survive. \n",
    "If there is a flock of ten ducks, how many pounds of insects do they need per day?\n",
    "ANSWER: Ducks need 3.5 pounds of insects each week. If there is a flock of 10 ducks, then they need 3.5 x 10 = 35 pounds of insects each week. If they need 35 pounds of insects each week, then they need 35 / 7 = 5 pounds of insects each day. The answer is 5. \n",
    "\n",
    "QUESTION: It takes Matthew 3 minutes to dig a small hole for shrubs and 10 minutes to dig a large hole for trees.\n",
    "How many hours will it take him to dig 30 small holes and 15 large holes?\n",
    "ANSWER: It takes Matthew 3 minutes to dig a small hole and 10 minutes to dig a large hole. So, it takes Matthew 3 x 30 = 90 minutes to dig 30 small holes. It takes Matthew 10 x 15 = 150 minutes to dig 15 large holes. So, it takes Matthew 90 + 150 = 240 minutes to dig 30 small holes and 15 large holes. 240 minutes is 4 hours. The answer is 4 hours. \n",
    "\n",
    "QUESTION: I have 10 liters of orange drink that are two-thirds water and I wish to add it to 15 liters of pineapple drink that is three-fifths water. \n",
    "But as I pour it, I spill one liter of the orange drink. How much water is in the remaining 24 liters?\n",
    "ANSWER:\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "list_of_messages = list()\n",
    "list_of_messages.append(system_message)\n",
    "list_of_messages.append(user_message)\n",
    "\n",
    "list_of_message_lists = list()\n",
    "list_of_message_lists.append(list_of_messages)\n",
    "\n",
    "prompt = convert_list_of_message_lists_to_input_prompt(list_of_message_lists, tokenizer)\n",
    "print(prompt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f0d2a25a-040b-4b7f-b0b6-a01baefa1178",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "dc08843eff714983a0d3bb59fb5421eb",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:362: UserWarning: `do_sample` is set to `False`. However, `temperature` is set to `0.9` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.\n",
      "  warnings.warn(\n",
      "/opt/conda/lib/python3.10/site-packages/transformers/generation/configuration_utils.py:367: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.\n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "from transformers import LlamaForCausalLM\n",
    "\n",
    "model = LlamaForCausalLM.from_pretrained(\n",
    "    model_checkpoint,\n",
    "    torch_dtype=torch.bfloat16,\n",
    "    low_cpu_mem_usage=True,\n",
    ")\n",
    "\n",
    "model = model.eval()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "703f96ed-08a1-466f-8b67-919ac7e1e1a3",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "prompt is 430 tokens\n"
     ]
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "\n",
    "tokenized_prompt = tokenizer(prompt)\n",
    "\n",
    "print(f'prompt is {len(tokenized_prompt[\"input_ids\"][0])} tokens')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "80143960-fc13-47ca-a1a1-4a22446eaebf",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from transformers import GenerationConfig\n",
    "\n",
    "generation_config = GenerationConfig(max_new_tokens=2000)                                      \n",
    "\n",
    "pipeline = pipeline(\"text-generation\", \n",
    "                    model=model, \n",
    "                    tokenizer=tokenizer, \n",
    "                    generation_config=generation_config)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d8c6b870-2484-4d64-8a57-2322cf4a99e1",
   "metadata": {
    "tags": []
   },
   "source": [
    "### This next cell takes about 10-15 minutes.  Please be patient."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "702a3695-8c9a-4978-8b90-5b39ab22cf8f",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "pipeline(prompt, return_full_text=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "88e87401-5390-4636-a4e5-87eaddfaa91e",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "availableInstances": [
   {
    "_defaultOrder": 0,
    "_isFastLaunch": true,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 4,
    "name": "ml.t3.medium",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 1,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.t3.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 2,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.t3.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 3,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.t3.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 4,
    "_isFastLaunch": true,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.m5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 5,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.m5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 6,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.m5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 7,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.m5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 8,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.m5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 9,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.m5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 10,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.m5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 11,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.m5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 12,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.m5d.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 13,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.m5d.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 14,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.m5d.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 15,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.m5d.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 16,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.m5d.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 17,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.m5d.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 18,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.m5d.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 19,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.m5d.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 20,
    "_isFastLaunch": false,
    "category": "General purpose",
    "gpuNum": 0,
    "hideHardwareSpecs": true,
    "memoryGiB": 0,
    "name": "ml.geospatial.interactive",
    "supportedImageNames": [
     "sagemaker-geospatial-v1-0"
    ],
    "vcpuNum": 0
   },
   {
    "_defaultOrder": 21,
    "_isFastLaunch": true,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 4,
    "name": "ml.c5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 22,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 8,
    "name": "ml.c5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 23,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.c5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 24,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.c5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 25,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 72,
    "name": "ml.c5.9xlarge",
    "vcpuNum": 36
   },
   {
    "_defaultOrder": 26,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 96,
    "name": "ml.c5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 27,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 144,
    "name": "ml.c5.18xlarge",
    "vcpuNum": 72
   },
   {
    "_defaultOrder": 28,
    "_isFastLaunch": false,
    "category": "Compute optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.c5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 29,
    "_isFastLaunch": true,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.g4dn.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 30,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.g4dn.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 31,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.g4dn.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 32,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.g4dn.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 33,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.g4dn.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 34,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.g4dn.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 35,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 61,
    "name": "ml.p3.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 36,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 244,
    "name": "ml.p3.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 37,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 488,
    "name": "ml.p3.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 38,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.p3dn.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 39,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.r5.large",
    "vcpuNum": 2
   },
   {
    "_defaultOrder": 40,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.r5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 41,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.r5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 42,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.r5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 43,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.r5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 44,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.r5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 45,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 512,
    "name": "ml.r5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 46,
    "_isFastLaunch": false,
    "category": "Memory Optimized",
    "gpuNum": 0,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.r5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 47,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 16,
    "name": "ml.g5.xlarge",
    "vcpuNum": 4
   },
   {
    "_defaultOrder": 48,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 32,
    "name": "ml.g5.2xlarge",
    "vcpuNum": 8
   },
   {
    "_defaultOrder": 49,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 64,
    "name": "ml.g5.4xlarge",
    "vcpuNum": 16
   },
   {
    "_defaultOrder": 50,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 128,
    "name": "ml.g5.8xlarge",
    "vcpuNum": 32
   },
   {
    "_defaultOrder": 51,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 1,
    "hideHardwareSpecs": false,
    "memoryGiB": 256,
    "name": "ml.g5.16xlarge",
    "vcpuNum": 64
   },
   {
    "_defaultOrder": 52,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 192,
    "name": "ml.g5.12xlarge",
    "vcpuNum": 48
   },
   {
    "_defaultOrder": 53,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 4,
    "hideHardwareSpecs": false,
    "memoryGiB": 384,
    "name": "ml.g5.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 54,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 768,
    "name": "ml.g5.48xlarge",
    "vcpuNum": 192
   },
   {
    "_defaultOrder": 55,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 1152,
    "name": "ml.p4d.24xlarge",
    "vcpuNum": 96
   },
   {
    "_defaultOrder": 56,
    "_isFastLaunch": false,
    "category": "Accelerated computing",
    "gpuNum": 8,
    "hideHardwareSpecs": false,
    "memoryGiB": 1152,
    "name": "ml.p4de.24xlarge",
    "vcpuNum": 96
   }
  ],
  "kernelspec": {
   "display_name": "Python 3 (Data Science 3.0)",
   "language": "python",
   "name": "python3__SAGEMAKER_INTERNAL__arn:aws:sagemaker:us-west-2:236514542706:image/sagemaker-data-science-310-v1"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}