{ "cells": [ { "cell_type": "markdown", "id": "ba7f6f98-70f2-4ca6-b999-eed03641ea87", "metadata": {}, "source": [ "### 1. 安装HuggingFace 并下载模型到本地" ] }, { "cell_type": "code", "execution_count": null, "id": "9f413314-c410-43d3-bb3a-ba0aa18ec1be", "metadata": { "tags": [] }, "outputs": [], "source": [ "!pip install huggingface-hub -Uqq\n", "!pip install -U sagemaker" ] }, { "cell_type": "code", "execution_count": null, "id": "be112a00-cbef-4387-b0d7-80e5e7b7030d", "metadata": { "tags": [] }, "outputs": [], "source": [ "from huggingface_hub import snapshot_download\n", "from pathlib import Path\n", "\n", "local_model_path = Path(\"./sentence2emb-model\")\n", "local_model_path.mkdir(exist_ok=True)\n", "model_name = \"shibing624/text2vec-base-chinese\"\n", "commit_hash = \"630e10fe8ee797b7bb24abd79e9b28a8f537b660\"" ] }, { "cell_type": "code", "execution_count": null, "id": "902798dc-227b-4191-ade7-b736571543ac", "metadata": { "tags": [] }, "outputs": [], "source": [ "snapshot_download(repo_id=model_name, revision=commit_hash, cache_dir=local_model_path)" ] }, { "cell_type": "markdown", "id": "a6b61ad8-a8c2-48c2-8539-e7c1e2afe773", "metadata": {}, "source": [ "### 2. 把模型拷贝到S3为后续部署做准备" ] }, { "cell_type": "code", "execution_count": null, "id": "5e1873f4-1bfe-4146-8297-584e9ad76fc9", "metadata": { "tags": [] }, "outputs": [], "source": [ "import sagemaker\n", "from sagemaker import image_uris\n", "import boto3\n", "import os\n", "import time\n", "import json\n", "\n", "role = sagemaker.get_execution_role() # execution role for the endpoint\n", "sess = sagemaker.session.Session() # sagemaker session for interacting with different AWS APIs\n", "bucket = sess.default_bucket() # bucket to house artifacts\n", "\n", "region = sess._region_name\n", "account_id = sess.account_id()\n", "\n", "s3_client = boto3.client(\"s3\")\n", "sm_client = boto3.client(\"sagemaker\")\n", "smr_client = boto3.client(\"sagemaker-runtime\")" ] }, { "cell_type": "code", "execution_count": null, "id": "68394e44-4d51-48ae-adc1-d02f520a5d4d", "metadata": { "tags": [] }, "outputs": [], "source": [ "s3_model_prefix = \"LLM-RAG/workshop/text2vec-base-model\" # folder where model checkpoint will go\n", "model_snapshot_path = list(local_model_path.glob(\"**/snapshots/*\"))[0]\n", "s3_code_prefix = \"LLM-RAG/workshop/text2vec_base_deploy_code\"\n", "print(f\"s3_code_prefix: {s3_code_prefix}\")\n", "print(f\"model_snapshot_path: {model_snapshot_path}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "0b9e177a-886d-4838-891e-2e612a3cbc9d", "metadata": { "tags": [] }, "outputs": [], "source": [ "!aws s3 cp --recursive {model_snapshot_path} s3://{bucket}/{s3_model_prefix}" ] }, { "cell_type": "markdown", "id": "59f35a6f-5988-42ec-87b0-de36eaebe41b", "metadata": { "tags": [] }, "source": [ "### 3. 模型部署准备（entrypoint脚本，容器镜像，服务配置）" ] }, { "cell_type": "code", "execution_count": null, "id": "86daea77-a7ae-46b8-8800-212d07ce5605", "metadata": { "tags": [] }, "outputs": [], "source": [ "inference_image_uri = (\n", " f\"763104351884.dkr.ecr.{region}.amazonaws.com/djl-inference:0.21.0-deepspeed0.8.3-cu117\"\n", ")\n", "\n", "#中国区需要替换为下面的image_uri\n", "# inference_image_uri = (\n", "# f\"727897471807.dkr.ecr.{region}.amazonaws.com.cn/djl-inference:0.21.0-deepspeed0.8.3-cu117\"\n", "# )\n", "\n", "print(f\"Image going to be used is ---- > {inference_image_uri}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "49435172-e6c5-492a-8dcb-43e3fffb0f5c", "metadata": { "tags": [] }, "outputs": [], "source": [ "!mkdir -p text2vec_base_deploy_code" ] }, { "cell_type": "code", "execution_count": null, "id": "70990dd3-431e-4dd0-a494-d26ceb454945", "metadata": { "tags": [] }, "outputs": [], "source": [ "%%writefile text2vec_base_deploy_code/model.py\n", "from djl_python import Input, Output\n", "import torch\n", "import logging\n", "import math\n", "import os\n", "from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, AutoModel\n", "\n", "device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')\n", "print(f'--device={device}')\n", "\n", "\n", "def load_model(properties):\n", " tensor_parallel = properties[\"tensor_parallel_degree\"]\n", " model_location = properties['model_dir']\n", " if \"model_id\" in properties:\n", " model_location = properties['model_id']\n", " logging.info(f\"Loading model in {model_location}\")\n", " \n", " tokenizer = AutoTokenizer.from_pretrained(model_location)\n", " \n", " model = AutoModel.from_pretrained(\n", " model_location, \n", " # device_map=\"balanced_low_0\", \n", " #load_in_8bit=True\n", " )\n", " # load the model on GPU\n", " model.to(device) \n", " model.requires_grad_(False)\n", " model.eval()\n", " \n", " return model, tokenizer\n", "\n", "\n", "model = None\n", "tokenizer = None\n", "generator = None\n", "\n", "def mean_pooling(model_output, attention_mask):\n", " token_embeddings = model_output[0].to(device) #First element of model_output contains all token embeddings\n", " input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float().to(device)\n", " return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)\n", "\n", "\n", "def handle(inputs: Input):\n", " global model, tokenizer\n", " if not model:\n", " model, tokenizer = load_model(inputs.get_properties())\n", "\n", " if inputs.is_empty():\n", " return None\n", " data = inputs.get_as_json()\n", " \n", " input_sentences = data[\"inputs\"]\n", " params = data[\"parameters\"]\n", " logging.info(f\"inputs: {input_sentences}\")\n", " logging.info(f\"parameters: {params}\")\n", " \n", " encoded_input = tokenizer(input_sentences, padding=True, truncation=True, max_length=512, return_tensors='pt').to(device)\n", " # Compute token embeddings\n", " with torch.no_grad():\n", " model_output = model(**encoded_input)\n", "\n", " # Perform pooling. In this case, max pooling.\n", " sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask']).to(device).cpu().numpy()\n", "\n", "# # preprocess\n", "# input_ids = tokenizer(input_sentences, return_tensors=\"pt\").input_ids\n", "# # pass inputs with all kwargs in data\n", "# if params is not None:\n", "# outputs = model.generate(input_ids, **params)\n", "# else:\n", "# outputs = model.generate(input_ids)\n", "\n", "# # postprocess the prediction\n", "# prediction = tokenizer.decode(outputs[0], skip_special_tokens=True)\n", " \n", " result = {\"sentence_embeddings\": sentence_embeddings}\n", " return Output().add_as_json(result)" ] }, { "cell_type": "code", "execution_count": null, "id": "e01a0f2a-a8d6-4134-a727-c5c0f1ad092b", "metadata": {}, "outputs": [], "source": [ "print(f\"option.s3url ==> s3://{bucket}/{s3_model_prefix}/\")" ] }, { "cell_type": "markdown", "id": "a1e1ecec-79cf-4ed4-bba1-95e2fe79daea", "metadata": {}, "source": [ "#### Note: option.s3url 需要按照自己的账号进行修改, 可以拷贝上一个cell的输出" ] }, { "cell_type": "code", "execution_count": null, "id": "ab5ee385-5c6c-493c-bd40-9b57ae0c8e1d", "metadata": { "tags": [] }, "outputs": [], "source": [ "%%writefile text2vec_base_deploy_code/serving.properties\n", "engine=Python\n", "option.tensor_parallel_degree=1\n", "option.s3url = s3://sagemaker-us-west-2-106839800180/LLM-RAG/workshop/text2vec-base-model/" ] }, { "cell_type": "markdown", "id": "685e38ed-341f-48e9-8cfd-57adee25176c", "metadata": { "tags": [] }, "source": [ "!rm s2e_model.tar.gz\n", "!cd text2vec_base_deploy_code && rm -rf \".ipynb_checkpoints\"\n", "!tar czvf s2e_model.tar.gz text2vec_base_deploy_code" ] }, { "cell_type": "code", "execution_count": null, "id": "1fabd7ce-b855-4569-857c-ad872662800b", "metadata": { "tags": [] }, "outputs": [], "source": [ "s3_code_artifact = sess.upload_data(\"s2e_model.tar.gz\", bucket, s3_code_prefix)\n", "print(f\"S3 Code or Model tar ball uploaded to --- > {s3_code_artifact}\")" ] }, { "cell_type": "markdown", "id": "18fb01ed-6bd3-4880-a647-cfd71e692820", "metadata": { "tags": [] }, "source": [ "### 4. 创建模型 & 创建endpoint" ] }, { "cell_type": "code", "execution_count": null, "id": "e6209d24-8473-4256-93d3-02e4e144386b", "metadata": { "tags": [] }, "outputs": [], "source": [ "from sagemaker.utils import name_from_base\n", "import boto3\n", "\n", "model_name = name_from_base(\"text2vec-base-chinese\")# name_from_base(\"st-paraphrase-mpnet-base-v2\") Note: Need to specify model_name\n", "print(model_name)\n", "print(f\"Image going to be used is ---- > {inference_image_uri}\")\n", "\n", "create_model_response = sm_client.create_model(\n", " ModelName=model_name,\n", " ExecutionRoleArn=role,\n", " PrimaryContainer={\n", " \"Image\": inference_image_uri,\n", " \"ModelDataUrl\": s3_code_artifact\n", " },\n", " \n", ")\n", "model_arn = create_model_response[\"ModelArn\"]\n", "\n", "print(f\"Created Model: {model_arn}\")" ] }, { "cell_type": "markdown", "id": "ad49970f-3d4d-41f1-ba1e-abfd378de150", "metadata": {}, "source": [ "#### 推理机型选择 (https://aws.amazon.com/cn/sagemaker/pricing/)\n", "- GPU\n", " + ml.g4dn.xlarge 按需价格 0.526 USD/Hour\n", "- CPU\n", " + ml.c5.xlarge 按需价格 0.204 USD/Hour" ] }, { "cell_type": "code", "execution_count": null, "id": "686abae8-5db7-4ebd-9fbf-5bd54f36c0ab", "metadata": { "tags": [] }, "outputs": [], "source": [ "endpoint_config_name = f\"{model_name}-config\"\n", "endpoint_name = f\"{model_name}-endpoint\"\n", "\n", "endpoint_config_response = sm_client.create_endpoint_config(\n", " EndpointConfigName=endpoint_config_name,\n", " ProductionVariants=[\n", " {\n", " \"VariantName\": \"variant1\",\n", " \"ModelName\": model_name,\n", " \"InstanceType\": \"ml.c5.xlarge\",\n", " \"InitialInstanceCount\": 1,\n", " # \"VolumeSizeInGB\" : 400,\n", " # \"ModelDataDownloadTimeoutInSeconds\": 2400,\n", " \"ContainerStartupHealthCheckTimeoutInSeconds\": 15*60,\n", " },\n", " ],\n", ")\n", "endpoint_config_response" ] }, { "cell_type": "code", "execution_count": null, "id": "f4c1df06-ae4a-42e2-9695-da0afa9ad734", "metadata": { "tags": [] }, "outputs": [], "source": [ "create_endpoint_response = sm_client.create_endpoint(\n", " EndpointName=f\"{endpoint_name}\", EndpointConfigName=endpoint_config_name\n", ")\n", "print(f\"Created Endpoint: {create_endpoint_response['EndpointArn']}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "d9c71240-6878-4fed-bf7d-2c1cf75f4ac5", "metadata": { "tags": [] }, "outputs": [], "source": [ "import time\n", "\n", "resp = sm_client.describe_endpoint(EndpointName=endpoint_name)\n", "status = resp[\"EndpointStatus\"]\n", "print(\"Status: \" + status)\n", "\n", "while status == \"Creating\":\n", " time.sleep(60)\n", " resp = sm_client.describe_endpoint(EndpointName=endpoint_name)\n", " status = resp[\"EndpointStatus\"]\n", " print(\"Status: \" + status)\n", "\n", "print(\"Arn: \" + resp[\"EndpointArn\"])\n", "print(\"Status: \" + status)" ] }, { "cell_type": "markdown", "id": "dddba20e-fc18-480d-9940-ae39695ac450", "metadata": {}, "source": [ "### 5. 模型测试" ] }, { "cell_type": "code", "execution_count": null, "id": "1f28db25-6996-440c-b004-14f96cfd982d", "metadata": { "tags": [] }, "outputs": [], "source": [ "def get_vector_by_sm_endpoint(questions, sm_client, endpoint_name):\n", " parameters = {\n", " # \"early_stopping\": True,\n", " # \"length_penalty\": 2.0,\n", " \"max_new_tokens\": 50,\n", " \"temperature\": 0,\n", " \"min_length\": 10,\n", " \"no_repeat_ngram_size\": 2,\n", " }\n", "\n", " response_model = sm_client.invoke_endpoint(\n", " EndpointName=endpoint_name,\n", " Body=json.dumps(\n", " {\n", " \"inputs\": questions,\n", " \"parameters\": parameters\n", " }\n", " ),\n", " ContentType=\"application/json\",\n", " )\n", " json_str = response_model['Body'].read().decode('utf8')\n", " json_obj = json.loads(json_str)\n", " embeddings = json_obj['sentence_embeddings']\n", " return embeddings" ] }, { "cell_type": "code", "execution_count": null, "id": "52d4f56a-092e-4a6a-a920-48550ec9f20c", "metadata": { "tags": [] }, "outputs": [], "source": [ "prompts1 = \"\"\"请问AWS Clean Rooms是多方都会收费吗？\"\"\"\n", "\n", "print(get_vector_by_sm_endpoint(prompts1, smr_client, endpoint_name))" ] }, { "cell_type": "code", "execution_count": null, "id": "aa0d6623-236d-4a5d-8360-4b07f8d8d40c", "metadata": { "tags": [] }, "outputs": [], "source": [ "!aws sagemaker delete-endpoint --endpoint-name text2vec-base-chinese-2023-06-14-01-29-59-579-endpoint" ] }, { "cell_type": "code", "execution_count": null, "id": "36281bf3-b6f5-450f-b1b8-9f1285b1dad0", "metadata": { "tags": [] }, "outputs": [], "source": [ "!aws sagemaker delete-endpoint-config --endpoint-config-name text2vec-base-chinese-2023-06-14-01-29-59-579-config" ] }, { "cell_type": "code", "execution_count": null, "id": "f9700aff", "metadata": {}, "outputs": [], "source": [ "!aws sagemaker delete-model --model-name text2vec-base-chinese-2023-06-14-01-29-59-579" ] } ], "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 } ], "instance_type": "ml.m5.large", "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 }