sagemaker/pr_2188/en/tutorials/jumpstart/jumpstart-quickstart.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quickstart - Deploy Hugging Face Models with SageMaker Jumpstart&quot;,&quot;local&quot;:&quot;quickstart---deploy-hugging-face-models-with-sagemaker-jumpstart&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Why use SageMaker JumpStart for Hugging Face models?&quot;,&quot;local&quot;:&quot;why-use-sagemaker-jumpstart-for-hugging-face-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;1. Prerequisites&quot;,&quot;local&quot;:&quot;1-prerequisites&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;2· Endpoint deployment&quot;,&quot;local&quot;:&quot;2-endpoint-deployment&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;3. Test interactively&quot;,&quot;local&quot;:&quot;3-test-interactively&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;4. Clean‑up&quot;,&quot;local&quot;:&quot;4-cleanup&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/sagemaker/pr_2188/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/entry/start.48a18f09.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/scheduler.aec39e6a.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/singletons.8e7a9ddc.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/paths.a4e52f32.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/entry/app.8481cdda.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/preload-helper.382cad4e.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/index.4ee0a2d0.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/nodes/0.52c1f0fb.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/nodes/17.ba3e641f.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.3c60bfa3.js">
		<link rel="modulepreload" href="/docs/sagemaker/pr_2188/en/_app/immutable/chunks/CodeBlock.543f5448.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Quickstart - Deploy Hugging Face Models with SageMaker Jumpstart&quot;,&quot;local&quot;:&quot;quickstart---deploy-hugging-face-models-with-sagemaker-jumpstart&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Why use SageMaker JumpStart for Hugging Face models?&quot;,&quot;local&quot;:&quot;why-use-sagemaker-jumpstart-for-hugging-face-models&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;1. Prerequisites&quot;,&quot;local&quot;:&quot;1-prerequisites&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;2· Endpoint deployment&quot;,&quot;local&quot;:&quot;2-endpoint-deployment&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;3. Test interactively&quot;,&quot;local&quot;:&quot;3-test-interactively&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;4. Clean‑up&quot;,&quot;local&quot;:&quot;4-cleanup&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="quickstart---deploy-hugging-face-models-with-sagemaker-jumpstart" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#quickstart---deploy-hugging-face-models-with-sagemaker-jumpstart"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Quickstart - Deploy Hugging Face Models with SageMaker Jumpstart</span></h1>  <h2 class="relative group"><a id="why-use-sagemaker-jumpstart-for-hugging-face-models" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#why-use-sagemaker-jumpstart-for-hugging-face-models"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Why use SageMaker JumpStart for Hugging Face models?</span></h2> <p data-svelte-h="svelte-c323bq">Amazon SageMaker JumpStart lets you deploy the most-popular open Hugging Face models with one click—inside your own AWS account. JumpStart offers a curated <a href="https://aws.amazon.com/sagemaker-ai/jumpstart/getting-started/?sagemaker-jumpstart-cards.sort-by=item.additionalFields.model-name&sagemaker-jumpstart-cards.sort-order=asc&awsf.sagemaker-jumpstart-filter-product-type=*all&awsf.sagemaker-jumpstart-filter-text=*all&awsf.sagemaker-jumpstart-filter-vision=*all&awsf.sagemaker-jumpstart-filter-tabular=*all&awsf.sagemaker-jumpstart-filter-audio-tasks=*all&awsf.sagemaker-jumpstart-filter-multimodal=*all&awsf.sagemaker-jumpstart-filter-RL=*all&awsm.page-sagemaker-jumpstart-cards=1&sagemaker-jumpstart-cards.q=qwen&sagemaker-jumpstart-cards.q_operator=AND" rel="nofollow">selection</a> of model checkpoints for various tasks, including text generation, embeddings, vision, audio, and more. Most models are deployed using the official <a href="https://huggingface.co/docs/sagemaker/main/en/dlcs/introduction" rel="nofollow">Hugging Face Deep Learning Containers</a> with a sensible default instance type, so you can move from idea to production in minutes.</p> <p data-svelte-h="svelte-glhkwk">In this quickstart guide, we will deploy <a href="https://huggingface.co/Qwen/Qwen2.5-14B-Instruct" rel="nofollow">Qwen/Qwen2.5-14B-Instruct</a>.</p>  <h2 class="relative group"><a id="1-prerequisites" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#1-prerequisites"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>1. Prerequisites</span></h2> <table data-svelte-h="svelte-170vxk4"><thead><tr><th></th> <th>Requirement</th></tr></thead> <tbody><tr><td>AWS account with SageMaker enabled</td> <td>An AWS account that will contain all your AWS resources.</td></tr> <tr><td>An IAM role to access SageMaker AI</td> <td>Learn more about how IAM works with SageMaker AI in this <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/security-iam.html" rel="nofollow">guide</a>.</td></tr> <tr><td>SageMaker Studio domain and user profile</td> <td>We recommend using SageMaker Studio for straightforward deployment and inference. Follow this <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/onboard-quick-start.html" rel="nofollow">guide</a>.</td></tr> <tr><td>Service quotas</td> <td>Most LLMs need GPU instances (e.g. ml.g5). Verify you have quota for <code>ml.g5.24xlarge</code> or <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/canvas-requesting-quota-increases.html" rel="nofollow">request it</a>.</td></tr></tbody></table> <blockquote data-svelte-h="svelte-p7runb"><p>[!WARNING][SageMaker Python SDK v3 has been recently released](<a href="https://github.com/aws/sagemaker-python-sdk" rel="nofollow">https://github.com/aws/sagemaker-python-sdk</a>), so unless specified otherwise, all the documentation and tutorials are still using the <a href="https://github.com/aws/sagemaker-python-sdk/tree/master-v2" rel="nofollow">SageMaker Python SDK v2</a>. We are actively working on updating all the tutorials and examples, but in the meantime make sure to install the SageMaker SDK as <code>pip install &quot;sagemaker&lt;3.0.0&quot;</code>.</p></blockquote>  <h2 class="relative group"><a id="2-endpoint-deployment" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#2-endpoint-deployment"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>2· Endpoint deployment</span></h2> <p data-svelte-h="svelte-el0n8y">Let’s explain how you would deploy a Hugging Face model to SageMaker browsing through the Jumpstart catalog:</p> <ol data-svelte-h="svelte-7ng80t"><li>Open SageMaker → JumpStart.</li> <li>Filter “Hugging Face” or search for your model (e.g. Qwen2.5-14B).</li> <li>Click Deploy → (optional) adjust instance size / count → Deploy.</li> <li>Wait until Endpoints shows In service.</li> <li>Copy the Endpoint name (or ARN) for later use.</li></ol> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sagemaker/jumpstart-deployment.gif" alt="JumpStart deployment demo" width="500"> <p data-svelte-h="svelte-1lzsyqk">Alternatively, you can also browse through the Hugging Face Model Hub:</p> <ol data-svelte-h="svelte-vh08fk"><li>Open the model page → Click Deploy → SageMaker → Jumpstart tab if model is available.</li> <li>Copy the code snippet and use it from a SageMaker Notebook instance.</li></ol> <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/sagemaker/hf-jumpstart-deployment.gif" alt="JumpStart deployment demo" width="500"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-comment"># SageMaker JumpStart provides APIs as part of SageMaker SDK that allow you to deploy and fine-tune models in network isolation using scripts that SageMaker maintains.</span>

<span class="hljs-keyword">from</span> sagemaker.jumpstart.model <span class="hljs-keyword">import</span> JumpStartModel


model = JumpStartModel(model_id=<span class="hljs-string">&quot;huggingface-llm-qwen2-5-14b-instruct&quot;</span>)
example_payloads = model.retrieve_all_examples()

predictor = model.deploy()

<span class="hljs-keyword">for</span> payload <span class="hljs-keyword">in</span> example_payloads:
    response = predictor.predict(payload.body)
    <span class="hljs-built_in">print</span>(<span class="hljs-string">&quot;Input:\n&quot;</span>, payload.body[payload.prompt_key])
    <span class="hljs-built_in">print</span>(<span class="hljs-string">&quot;Output:\n&quot;</span>, response[<span class="hljs-number">0</span>][<span class="hljs-string">&quot;generated_text&quot;</span>], <span class="hljs-string">&quot;\n\n===============\n&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-knhstf">The endpoint creation can take several minutes, depending on the size of the model.</p>  <h2 class="relative group"><a id="3-test-interactively" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#3-test-interactively"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>3. Test interactively</span></h2> <p data-svelte-h="svelte-v65zqa">If you deployed through the console, you need to grab the endpoint ARN and reuse in your code.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> sagemaker.predictor <span class="hljs-keyword">import</span> retrieve_default
endpoint_name = <span class="hljs-string">&quot;MY ENDPOINT NAME&quot;</span>
predictor = retrieve_default(endpoint_name)
payload = {
    <span class="hljs-string">&quot;messages&quot;</span>: [
        {
            <span class="hljs-string">&quot;role&quot;</span>: <span class="hljs-string">&quot;system&quot;</span>,
            <span class="hljs-string">&quot;content&quot;</span>: <span class="hljs-string">&quot;You are a passionate data scientist.&quot;</span>
        },
        {
            <span class="hljs-string">&quot;role&quot;</span>: <span class="hljs-string">&quot;user&quot;</span>,
            <span class="hljs-string">&quot;content&quot;</span>: <span class="hljs-string">&quot;what is machine learning?&quot;</span>
        }
    ],
    <span class="hljs-string">&quot;max_tokens&quot;</span>: <span class="hljs-number">2048</span>,
    <span class="hljs-string">&quot;temperature&quot;</span>: <span class="hljs-number">0.7</span>,
    <span class="hljs-string">&quot;top_p&quot;</span>: <span class="hljs-number">0.9</span>,
    <span class="hljs-string">&quot;stream&quot;</span>: <span class="hljs-literal">False</span>
}

response = predictor.predict(payload)
<span class="hljs-built_in">print</span>(response)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-r63eq3">The endpoint support the Open AI API specification.</p>  <h2 class="relative group"><a id="4-cleanup" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#4-cleanup"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>4. Clean‑up</span></h2> <p data-svelte-h="svelte-t814jl">To avoid incurring unnecessary costs, when you’re done, delete the SageMaker endpoints in the Deployments → Endpoints console or using the following code snippets:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->predictor.delete_model()
predictor.delete_endpoint()<!-- HTML_TAG_END --></pre></div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/sagemaker/source/tutorials/jumpstart/jumpstart-quickstart.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_16a821l = {
						assets: "/docs/sagemaker/pr_2188/en",
						base: "/docs/sagemaker/pr_2188/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/sagemaker/pr_2188/en/_app/immutable/entry/start.48a18f09.js"),
						import("/docs/sagemaker/pr_2188/en/_app/immutable/entry/app.8481cdda.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 17],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>