{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a07b4596-d0ba-453b-b578-6de2953eccf2",
   "metadata": {},
   "source": [
    "# Deploy Models\n",
    "\n",
    "This notebook deploys two large language models (LLMs): one for generating embeddings and another for a question answering task. These models are then used in the `embed_data.ipynb` notebook and the `qa-w-rag-finetuned-llm` Lambda function."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6454bf8a-e910-489e-a255-853932c0a67d",
   "metadata": {},
   "source": [
    "In this notebook we are deploying the [`FLAN-T5 XXL`](https://huggingface.co/google/flan-t5-xxl) model as the LLM for generating the response to questions and the [`GPT-J-6B`](https://huggingface.co/EleutherAI/gpt-j-6b) as the LLM for generating embeddings."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b7844155-3341-475f-b68d-7b4092e47b35",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install --upgrade sagemaker --quiet"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a62ece34-eed7-4fa4-b74b-80302150b432",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "import time\n",
    "import logging\n",
    "import sagemaker, boto3, json\n",
    "from sagemaker.model import Model\n",
    "from sagemaker.session import Session\n",
    "from sagemaker.predictor import Predictor\n",
    "from sagemaker.utils import name_from_base\n",
    "from sagemaker import image_uris, model_uris, script_uris, hyperparameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "fe90e81a-08ef-4d03-8059-11fafba14c4c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# global constants\n",
    "APP_NAME = \"qa-w-rag\"\n",
    "EMBEDDING_MODEL = \"huggingface-textembedding-gpt-j-6b\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c55b4ca0-dedf-4706-b9df-04d7a98a57d6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "logger = logging.getLogger()\n",
    "logging.basicConfig(format='%(asctime)s,%(module)s,%(processName)s,%(levelname)s,%(message)s', level=logging.INFO, stream=sys.stderr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "aee0c720-4641-4321-acc3-13a6069d8013",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-02 14:22:28,427,credentials,MainProcess,INFO,Found credentials from IAM Role: BaseNotebookInstanceEc2InstanceRole\n",
      "2023-05-02 14:22:28,766,credentials,MainProcess,INFO,Found credentials from IAM Role: BaseNotebookInstanceEc2InstanceRole\n",
      "2023-05-02 14:22:28,872,232507896,MainProcess,INFO,aws_role=arn:aws:iam::015469603702:role/SageMakerRepoRole, aws_region=us-east-1\n"
     ]
    }
   ],
   "source": [
    "sagemaker_session = Session()\n",
    "aws_role = sagemaker_session.get_caller_identity_arn()\n",
    "aws_region = boto3.Session().region_name\n",
    "sess = sagemaker.Session()\n",
    "model_version = \"*\"\n",
    "logger.info(f\"aws_role={aws_role}, aws_region={aws_region}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "50e1c44e-28bf-4caf-a298-621e4687aff7",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def parse_response_model_flan_t5(query_response):\n",
    "    model_predictions = json.loads(query_response[\"Body\"].read())\n",
    "    generated_text = model_predictions[\"generated_texts\"]\n",
    "    return generated_text"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "d58a8b8c-ca42-4557-867d-51f2489d064e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "MODEL_CONFIG_LIST = [\n",
    "    {\n",
    "        \"model_id\": \"huggingface-text2text-flan-t5-xxl\",\n",
    "        \"model_version\": \"*\",\n",
    "        \"instance_type\": \"ml.g5.12xlarge\",\n",
    "        \"instance_count\": 1,\n",
    "        \"env\": {\"TS_DEFAULT_WORKERS_PER_MODEL\": \"1\"},\n",
    "        \"predictor_cls\": Predictor\n",
    "    },\n",
    "    {\n",
    "        \"model_id\": \"huggingface-textembedding-gpt-j-6b\",\n",
    "        \"model_version\": \"*\",\n",
    "        \"instance_type\": \"ml.g5.24xlarge\",\n",
    "        \"instance_count\": 1,\n",
    "        \"env\": {\"TS_DEFAULT_WORKERS_PER_MODEL\": \"2\"},\n",
    "    }\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "0e7655ad-50c0-42d1-9b1e-47bd081ccd46",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-02 14:22:28,893,2580055255,MainProcess,INFO,going to deploy model={'model_id': 'huggingface-text2text-flan-t5-xxl', 'model_version': '*', 'instance_type': 'ml.g5.12xlarge', 'instance_count': 1, 'env': {'TS_DEFAULT_WORKERS_PER_MODEL': '1'}, 'predictor_cls': <class 'sagemaker.predictor.Predictor'>}, endpoint_name=qa-w-rag-huggingface-text2text-flan-t5--2023-05-02-14-22-28-892\n",
      "2023-05-02 14:22:28,928,credentials,MainProcess,INFO,Found credentials from IAM Role: BaseNotebookInstanceEc2InstanceRole\n",
      "2023-05-02 14:22:29,436,2580055255,MainProcess,INFO,deploy_image_uri=763104351884.dkr.ecr.us-east-1.amazonaws.com/pytorch-inference:1.12.0-gpu-py38, model_uri=s3://jumpstart-cache-prod-us-east-1/huggingface-infer/prepack/v1.0.2/infer-prepack-huggingface-text2text-flan-t5-xxl.tar.gz\n",
      "2023-05-02 14:22:29,532,session,MainProcess,INFO,Creating model with name: qa-w-rag-huggingface-text2text-flan-t5--2023-05-02-14-22-28-892\n",
      "2023-05-02 14:22:30,448,session,MainProcess,INFO,Creating endpoint-config with name qa-w-rag-huggingface-text2text-flan-t5--2023-05-02-14-22-28-892\n",
      "2023-05-02 14:22:30,961,session,MainProcess,INFO,Creating endpoint with name qa-w-rag-huggingface-text2text-flan-t5--2023-05-02-14-22-28-892\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-------------!"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-02 14:29:33,163,2580055255,MainProcess,INFO,\u001b[1mmodel=huggingface-text2text-flan-t5-xxl has been deployed successfully at endpoint=qa-w-rag-huggingface-text2text-flan-t5--2023-05-02-14-22-28-892, took 424.27027797698975seconds\u001b[0m\n",
      "\n",
      "2023-05-02 14:29:33,163,2580055255,MainProcess,INFO,going to deploy model={'model_id': 'huggingface-textembedding-gpt-j-6b', 'model_version': '*', 'instance_type': 'ml.g5.24xlarge', 'instance_count': 1, 'env': {'TS_DEFAULT_WORKERS_PER_MODEL': '2'}}, endpoint_name=qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163\n",
      "2023-05-02 14:29:33,325,2580055255,MainProcess,INFO,deploy_image_uri=763104351884.dkr.ecr.us-east-1.amazonaws.com/pytorch-inference:1.12.0-gpu-py38, model_uri=s3://jumpstart-cache-prod-us-east-1/huggingface-infer/prepack/v1.0.0/infer-prepack-huggingface-textembedding-gpt-j-6b.tar.gz\n",
      "2023-05-02 14:29:33,353,session,MainProcess,INFO,Creating model with name: qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163\n",
      "2023-05-02 14:29:34,205,session,MainProcess,INFO,Creating endpoint-config with name qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163\n",
      "2023-05-02 14:29:34,661,session,MainProcess,INFO,Creating endpoint with name qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-----------!"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-02 14:35:36,697,2580055255,MainProcess,INFO,\u001b[1mmodel=huggingface-textembedding-gpt-j-6b has been deployed successfully at endpoint=qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163, took 363.5339434146881seconds\u001b[0m\n",
      "\n"
     ]
    }
   ],
   "source": [
    "newline, bold, unbold = \"\\n\", \"\\033[1m\", \"\\033[0m\"\n",
    "\n",
    "for model in MODEL_CONFIG_LIST: \n",
    "    start = time.time()\n",
    "    endpoint_name = name_from_base(f\"{APP_NAME}-{model['model_id']}\")\n",
    "    logger.info(f\"going to deploy model={model}, endpoint_name={endpoint_name}\")    \n",
    "    # Retrieve the inference container uri. This is the base HuggingFace container image for the default model above.\n",
    "    deploy_image_uri = image_uris.retrieve(\n",
    "        region=None,\n",
    "        framework=None,  # automatically inferred from model_id\n",
    "        image_scope=\"inference\",\n",
    "        model_id=model['model_id'],\n",
    "        model_version=model['model_version'],\n",
    "        instance_type=model['instance_type'],\n",
    "    )\n",
    "    # Retrieve the model uri.\n",
    "    model_uri = model_uris.retrieve(\n",
    "        model_id=model['model_id'], model_version=model['model_version'], model_scope=\"inference\"\n",
    "    )\n",
    "    logger.info(f\"deploy_image_uri={deploy_image_uri}, model_uri={model_uri}\")\n",
    "    model_inference = Model(\n",
    "        image_uri=deploy_image_uri,\n",
    "        model_data=model_uri,\n",
    "        role=aws_role,\n",
    "        predictor_cls=model.get(\"predictor_cls\"),\n",
    "        name=endpoint_name,\n",
    "        env=model['env'],\n",
    "    )\n",
    "    model_predictor_inference = model_inference.deploy(\n",
    "        initial_instance_count=model['instance_count'],\n",
    "        instance_type=model['instance_type'],\n",
    "        predictor_cls=model.get(\"predictor_cls\"),\n",
    "        endpoint_name=endpoint_name,\n",
    "    )\n",
    "    time_taken = time.time() - start\n",
    "    logger.info(f\"{bold}model={model['model_id']} has been deployed successfully at endpoint={endpoint_name}, took {time_taken}seconds{unbold}{newline}\")\n",
    "    model[\"endpoint_name\"] = endpoint_name"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1bc50a11-5630-4dc4-8b3b-a3dcf70e69a3",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-02 14:35:36,705,4061947677,MainProcess,INFO,EMBEDDING_MODEL=huggingface-textembedding-gpt-j-6b,   embedding_model_endpoint_name=qa-w-rag-huggingface-textembedding-gpt--2023-05-02-14-29-33-163\n"
     ]
    }
   ],
   "source": [
    "embedding_model_endpoint_name = None\n",
    "for model in MODEL_CONFIG_LIST:\n",
    "    if model['model_id'] == EMBEDDING_MODEL:\n",
    "        embedding_model_endpoint_name = model['endpoint_name']\n",
    "        logger.info(f\"EMBEDDING_MODEL={EMBEDDING_MODEL},   embedding_model_endpoint_name={embedding_model_endpoint_name}\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "630e26d5-345b-48af-95d5-be13bb17d3a4",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stored 'embedding_model_endpoint_name' (str)\n"
     ]
    }
   ],
   "source": [
    "%store embedding_model_endpoint_name"
   ]
  }
 ],
 "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
   }
  ],
  "instance_type": "ml.m5.large",
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_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": "3.10.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}