Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / sagemaker /pr_2709 /en /reference /inference-toolkit.html

HuggingFaceDocBuilder

3 days ago

download

raw

31.1 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Inference Toolkit API","local":"inference-toolkit-api","sections":[{"title":"Supported tasks","local":"supported-tasks","sections":[],"depth":2},{"title":"Request examples","local":"request-examples","sections":[],"depth":2},{"title":"Environment variables","local":"environment-variables","sections":[],"depth":2}],"depth":1}"/>
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/entry/start.COiK-bUV.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/UGDyBJsP.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/Paddn1qZ.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/entry/app.CjYANwwM.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/Beft82ym.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/Ds9Xs-bq.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/DnXYL5Yp.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/nodes/0.CsY3iCn7.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/CxJVP3KE.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/nodes/22.BfbEdMen.js" rel="modulepreload">
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/chunks/Cz9gzD1e.js" rel="modulepreload">
	<!--1pu3mmd--><meta name="hf:doc:metadata" content="{"title":"Inference Toolkit API","local":"inference-toolkit-api","sections":[{"title":"Supported tasks","local":"supported-tasks","sections":[],"depth":2},{"title":"Request examples","local":"request-examples","sections":[],"depth":2},{"title":"Environment variables","local":"environment-variables","sections":[],"depth":2}],"depth":1}"/><!---->
	<link href="/docs/sagemaker/pr_2709/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><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> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="inference-toolkit-api" 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="#inference-toolkit-api"><span><svg 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>Inference Toolkit API</span></h1><!--]--><!----> <blockquote class="warning"><p>The SageMaker Hugging Face Inference Toolkit is in maintenance mode and will be deprecated. For new deployments, prefer the engine-based DLCs — <a href="../get-started/dlcs">vLLM, SGLang, TEI, or llama.cpp</a> — which offer better performance and active development. <a href="https://github.com/huggingface/hf-serve" rel="nofollow">hf-serve</a> is the experimental successor.</p></blockquote> <p>The <a href="https://github.com/aws/sagemaker-huggingface-inference-toolkit" rel="nofollow">SageMaker Hugging Face Inference Toolkit</a> is the zero-code serving layer inside the Hugging Face PyTorch inference DLC. It loads a model from the Hub — or from your own <code>model.tar.gz</code> — and serves it through a 🤗 Transformers <a href="https://huggingface.co/docs/transformers/main_classes/pipelines" rel="nofollow"><code>pipeline</code></a>, so you can deploy without writing any serving code. See <a href="../tutorials/sagemaker-sdk/deploy-sagemaker-sdk">Deploy models with the SageMaker SDK</a> for the deployment flow.</p> <p>Requests take the model input in the <code>inputs</code> key and optional <code>pipeline</code> parameters in the <code>parameters</code> key. You can provide any of the supported <code>kwargs</code> from <code>pipelines</code> as <code>parameters</code>.</p> <!--[1--><h2 class="relative group"><a id="supported-tasks" 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="#supported-tasks"><span><svg 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>Supported tasks</span></h2><!--]--><!----> <ul><li><strong><code>text-classification</code></strong></li> <li><strong><code>sentiment-analysis</code></strong></li> <li><strong><code>token-classification</code></strong></li> <li><strong><code>feature-extraction</code></strong></li> <li><strong><code>fill-mask</code></strong></li> <li><strong><code>summarization</code></strong></li> <li><strong><code>translation_xx_to_yy</code></strong></li> <li><strong><code>text2text-generation</code></strong></li> <li><strong><code>text-generation</code></strong></li> <li><strong><code>audio-classification</code></strong></li> <li><strong><code>automatic-speech-recognition</code></strong></li> <li><strong><code>conversational</code></strong></li> <li><strong><code>image-classification</code></strong></li> <li><strong><code>image-segmentation</code></strong></li> <li><strong><code>object-detection</code></strong></li> <li><strong><code>table-question-answering</code></strong></li> <li><strong><code>zero-shot-classification</code></strong></li> <li><strong><code>zero-shot-image-classification</code></strong></li></ul> <!--[1--><h2 class="relative group"><a id="request-examples" 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="#request-examples"><span><svg 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>Request examples</span></h2><!--]--><!----> <p><strong><code>text-classification</code></strong></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 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="language-json "><!----><span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"inputs"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"The documentation was clear and the deployment worked on the first try."</span>
	<span class="hljs-punctuation">}</span><!----></pre></div><!----> <p><strong><code>question-answering</code></strong></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 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="language-json "><!----><span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"inputs"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"question"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"Where is the model served?"</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"context"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"The model is served on a SageMaker endpoint inside your AWS account."</span>
	<span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">}</span><!----></pre></div><!----> <p><strong><code>zero-shot-classification</code></strong></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 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="language-json "><!----><span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"inputs"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!"</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"parameters"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"candidate_labels"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-string">"refund"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"legal"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"faq"</span><span class="hljs-punctuation">]</span>
	<span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">}</span><!----></pre></div><!----> <p><strong><code>table-question-answering</code></strong></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 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="language-json "><!----><span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"inputs"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"query"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"How many stars does the transformers repository have?"</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"table"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"Repository"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-string">"Transformers"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"Datasets"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"Tokenizers"</span><span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"Stars"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-string">"36542"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"4512"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"3934"</span><span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"Contributors"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-string">"651"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"77"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"34"</span><span class="hljs-punctuation">]</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"Programming language"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">[</span><span class="hljs-string">"Python"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"Python"</span><span class="hljs-punctuation">,</span> <span class="hljs-string">"Rust, Python and NodeJS"</span><span class="hljs-punctuation">]</span>
	<span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">}</span><!----></pre></div><!----> <p><strong>Parameterized request</strong> (any <code>pipeline</code> kwargs go in <code>parameters</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 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="language-json "><!----><span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"inputs"</span><span class="hljs-punctuation">:</span> <span class="hljs-string">"Hugging Face makes open-source AI tools and hosts a large catalog of models and datasets."</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"parameters"</span><span class="hljs-punctuation">:</span> <span class="hljs-punctuation">{</span>
	<span class="hljs-attr">"repetition_penalty"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">4.0</span><span class="hljs-punctuation">,</span>
	<span class="hljs-attr">"length_penalty"</span><span class="hljs-punctuation">:</span> <span class="hljs-number">1.5</span>
	<span class="hljs-punctuation">}</span>
	<span class="hljs-punctuation">}</span><!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="environment-variables" 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="#environment-variables"><span><svg 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>Environment variables</span></h2><!--]--><!----> <p>The Inference Toolkit reads Hugging Face specific environment variables at deploy time:</p> <p><strong><code>HF_TASK</code></strong></p> <p><code>HF_TASK</code> defines the task for the 🤗 Transformers <code>pipeline</code>. See <a href="https://huggingface.co/docs/transformers/main_classes/pipelines" rel="nofollow">here</a> for a complete list of tasks.</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 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="language-bash "><!---->HF_TASK=<span class="hljs-string">"question-answering"</span><!----></pre></div><!----> <p><strong><code>HF_MODEL_ID</code></strong></p> <p><code>HF_MODEL_ID</code> defines the model ID which is automatically loaded from <a href="https://huggingface.co/models" rel="nofollow">hf.co/models</a> when creating a SageMaker endpoint. Any public model on the Hub can be loaded this way.</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 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="language-bash "><!---->HF_MODEL_ID=<span class="hljs-string">"cardiffnlp/twitter-roberta-base-sentiment-latest"</span><!----></pre></div><!----> <p><strong><code>HF_MODEL_REVISION</code></strong></p> <p><code>HF_MODEL_REVISION</code> is an extension to <code>HF_MODEL_ID</code> and allows you to define or pin a model revision to make sure you always load the same model on your SageMaker endpoint.</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 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="language-bash "><!---->HF_MODEL_REVISION=<span class="hljs-string">"03b4d196c19d0a73c7e0322684e97db1ec397613"</span><!----></pre></div><!----> <p><strong><code>HF_API_TOKEN</code></strong></p> <p><code>HF_API_TOKEN</code> defines your Hugging Face authorization token. The <code>HF_API_TOKEN</code> is used as a HTTP bearer authorization for remote files like private models. You can find your token under <a href="https://huggingface.co/settings/tokens" rel="nofollow">Settings</a> of your Hugging Face account.</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 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="language-bash "><!---->HF_API_TOKEN=<span class="hljs-string">"hf_XXXXXXXXXXXXXXXXXXXXXXXXXXXXX"</span><!----></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/reference/inference-toolkit.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><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->

	<script>
	{
	__sveltekit_dwws3f = {
	base: "/docs/sagemaker/pr_2709/en",
	assets: "/docs/sagemaker/pr_2709/en"
	};

	const element = document.currentScript.parentElement;

	Promise.all([
	import("/docs/sagemaker/pr_2709/en/_app/immutable/entry/start.COiK-bUV.js"),
	import("/docs/sagemaker/pr_2709/en/_app/immutable/entry/app.CjYANwwM.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 22],
	data: [null,null],
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 31.1 kB
Xet hash:: f522748fed536da3f4a4253267078c656fd948ecad40c6ebf8cf7555871c730d

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.