Buckets:

download
raw
140 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;models&quot;,&quot;local&quot;:&quot;models&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;On this page&quot;,&quot;local&quot;:&quot;on-this-page&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Classes&quot;,&quot;local&quot;:&quot;classes&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;AutoModel&quot;,&quot;local&quot;:&quot;automodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSequenceClassification&quot;,&quot;local&quot;:&quot;automodelforsequenceclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTokenClassification&quot;,&quot;local&quot;:&quot;automodelfortokenclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSeq2SeqLM&quot;,&quot;local&quot;:&quot;automodelforseq2seqlm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSpeechSeq2Seq&quot;,&quot;local&quot;:&quot;automodelforspeechseq2seq&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTextToSpectrogram&quot;,&quot;local&quot;:&quot;automodelfortexttospectrogram&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTextToWaveform&quot;,&quot;local&quot;:&quot;automodelfortexttowaveform&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForCausalLM&quot;,&quot;local&quot;:&quot;automodelforcausallm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForMaskedLM&quot;,&quot;local&quot;:&quot;automodelformaskedlm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForQuestionAnswering&quot;,&quot;local&quot;:&quot;automodelforquestionanswering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForVision2Seq&quot;,&quot;local&quot;:&quot;automodelforvision2seq&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageClassification&quot;,&quot;local&quot;:&quot;automodelforimageclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageSegmentation&quot;,&quot;local&quot;:&quot;automodelforimagesegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSemanticSegmentation&quot;,&quot;local&quot;:&quot;automodelforsemanticsegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForUniversalSegmentation&quot;,&quot;local&quot;:&quot;automodelforuniversalsegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForObjectDetection&quot;,&quot;local&quot;:&quot;automodelforobjectdetection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForZeroShotObjectDetection&quot;,&quot;local&quot;:&quot;automodelforzeroshotobjectdetection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForMaskGeneration&quot;,&quot;local&quot;:&quot;automodelformaskgeneration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForCTC&quot;,&quot;local&quot;:&quot;automodelforctc&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioClassification&quot;,&quot;local&quot;:&quot;automodelforaudioclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForXVector&quot;,&quot;local&quot;:&quot;automodelforxvector&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioFrameClassification&quot;,&quot;local&quot;:&quot;automodelforaudioframeclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForDocumentQuestionAnswering&quot;,&quot;local&quot;:&quot;automodelfordocumentquestionanswering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageMatting&quot;,&quot;local&quot;:&quot;automodelforimagematting&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageToImage&quot;,&quot;local&quot;:&quot;automodelforimagetoimage&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForDepthEstimation&quot;,&quot;local&quot;:&quot;automodelfordepthestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForNormalEstimation&quot;,&quot;local&quot;:&quot;automodelfornormalestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForPoseEstimation&quot;,&quot;local&quot;:&quot;automodelforposeestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageFeatureExtraction&quot;,&quot;local&quot;:&quot;automodelforimagefeatureextraction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageTextToText&quot;,&quot;local&quot;:&quot;automodelforimagetexttotext&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioTextToText&quot;,&quot;local&quot;:&quot;automodelforaudiotexttotext&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;PreTrainedModel&quot;,&quot;local&quot;:&quot;pretrainedmodel&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PreTrainedModel(model_inputs)&quot;,&quot;local&quot;:&quot;pretrainedmodelmodelinputs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.constructor(config, sessions, configs)&quot;,&quot;local&quot;:&quot;pretrainedmodelconstructorconfig-sessions-configs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.dispose()&quot;,&quot;local&quot;:&quot;pretrainedmodeldispose&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.from_pretrained(pretrained_model_name_or_path, options)&quot;,&quot;local&quot;:&quot;pretrainedmodelfrompretrainedpretrainedmodelnameorpath-options&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.forward(model_inputs)&quot;,&quot;local&quot;:&quot;pretrainedmodelforwardmodelinputs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.generation_config&quot;,&quot;local&quot;:&quot;pretrainedmodelgenerationconfig&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.generate(options)&quot;,&quot;local&quot;:&quot;pretrainedmodelgenerateoptions&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3}],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
<link href="/docs/transformers.js/pr_1665/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/entry/start.cb58eb6f.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/scheduler.6efaaf90.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/singletons.08239980.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/paths.611c3944.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/entry/app.9eafcf9d.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/preload-helper.4b821645.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/index.eb3e1f0f.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/nodes/0.d361a553.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/nodes/11.518c7654.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.699f2734.js">
<link rel="modulepreload" href="/docs/transformers.js/pr_1665/en/_app/immutable/chunks/CodeBlock.b303f0b9.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;models&quot;,&quot;local&quot;:&quot;models&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;On this page&quot;,&quot;local&quot;:&quot;on-this-page&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Classes&quot;,&quot;local&quot;:&quot;classes&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;AutoModel&quot;,&quot;local&quot;:&quot;automodel&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSequenceClassification&quot;,&quot;local&quot;:&quot;automodelforsequenceclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTokenClassification&quot;,&quot;local&quot;:&quot;automodelfortokenclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSeq2SeqLM&quot;,&quot;local&quot;:&quot;automodelforseq2seqlm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSpeechSeq2Seq&quot;,&quot;local&quot;:&quot;automodelforspeechseq2seq&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTextToSpectrogram&quot;,&quot;local&quot;:&quot;automodelfortexttospectrogram&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForTextToWaveform&quot;,&quot;local&quot;:&quot;automodelfortexttowaveform&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForCausalLM&quot;,&quot;local&quot;:&quot;automodelforcausallm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForMaskedLM&quot;,&quot;local&quot;:&quot;automodelformaskedlm&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForQuestionAnswering&quot;,&quot;local&quot;:&quot;automodelforquestionanswering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForVision2Seq&quot;,&quot;local&quot;:&quot;automodelforvision2seq&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageClassification&quot;,&quot;local&quot;:&quot;automodelforimageclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageSegmentation&quot;,&quot;local&quot;:&quot;automodelforimagesegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForSemanticSegmentation&quot;,&quot;local&quot;:&quot;automodelforsemanticsegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForUniversalSegmentation&quot;,&quot;local&quot;:&quot;automodelforuniversalsegmentation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForObjectDetection&quot;,&quot;local&quot;:&quot;automodelforobjectdetection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForZeroShotObjectDetection&quot;,&quot;local&quot;:&quot;automodelforzeroshotobjectdetection&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForMaskGeneration&quot;,&quot;local&quot;:&quot;automodelformaskgeneration&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForCTC&quot;,&quot;local&quot;:&quot;automodelforctc&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioClassification&quot;,&quot;local&quot;:&quot;automodelforaudioclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForXVector&quot;,&quot;local&quot;:&quot;automodelforxvector&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioFrameClassification&quot;,&quot;local&quot;:&quot;automodelforaudioframeclassification&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForDocumentQuestionAnswering&quot;,&quot;local&quot;:&quot;automodelfordocumentquestionanswering&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageMatting&quot;,&quot;local&quot;:&quot;automodelforimagematting&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageToImage&quot;,&quot;local&quot;:&quot;automodelforimagetoimage&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForDepthEstimation&quot;,&quot;local&quot;:&quot;automodelfordepthestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForNormalEstimation&quot;,&quot;local&quot;:&quot;automodelfornormalestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForPoseEstimation&quot;,&quot;local&quot;:&quot;automodelforposeestimation&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageFeatureExtraction&quot;,&quot;local&quot;:&quot;automodelforimagefeatureextraction&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForImageTextToText&quot;,&quot;local&quot;:&quot;automodelforimagetexttotext&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;AutoModelForAudioTextToText&quot;,&quot;local&quot;:&quot;automodelforaudiotexttotext&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;PreTrainedModel&quot;,&quot;local&quot;:&quot;pretrainedmodel&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;PreTrainedModel(model_inputs)&quot;,&quot;local&quot;:&quot;pretrainedmodelmodelinputs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.constructor(config, sessions, configs)&quot;,&quot;local&quot;:&quot;pretrainedmodelconstructorconfig-sessions-configs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.dispose()&quot;,&quot;local&quot;:&quot;pretrainedmodeldispose&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.from_pretrained(pretrained_model_name_or_path, options)&quot;,&quot;local&quot;:&quot;pretrainedmodelfrompretrainedpretrainedmodelnameorpath-options&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.forward(model_inputs)&quot;,&quot;local&quot;:&quot;pretrainedmodelforwardmodelinputs&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.generation_config&quot;,&quot;local&quot;:&quot;pretrainedmodelgenerationconfig&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4},{&quot;title&quot;:&quot;PreTrainedModel.generate(options)&quot;,&quot;local&quot;:&quot;pretrainedmodelgenerateoptions&quot;,&quot;sections&quot;:[],&quot;depth&quot;:4}],&quot;depth&quot;:3}],&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="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="#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>models</span></h1> <p data-svelte-h="svelte-1suplhp">Definitions of all models available in Transformers.js.</p> <p data-svelte-h="svelte-1tjmd7w">We also provide other <code>AutoModel</code>s (listed below), which you can use in the same way as the Python library. For example:</p> <p data-svelte-h="svelte-1k8gtid"><strong>Example:</strong> Load and run an <code>AutoModel</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModel</span>, <span class="hljs-title class_">AutoTokenizer</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> tokenizer = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoTokenizer</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/bert-base-uncased&#x27;</span>);
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModel</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/bert-base-uncased&#x27;</span>);
<span class="hljs-keyword">const</span> inputs = <span class="hljs-keyword">await</span> <span class="hljs-title function_">tokenizer</span>(<span class="hljs-string">&#x27;I love transformers!&#x27;</span>);
<span class="hljs-keyword">const</span> { logits } = <span class="hljs-keyword">await</span> <span class="hljs-title function_">model</span>(inputs);
<span class="hljs-comment">// Tensor {</span>
<span class="hljs-comment">// data: Float32Array(183132) [-7.117443084716797, -7.107812881469727, -7.092104911804199, ...]</span>
<span class="hljs-comment">// dims: (3) [1, 6, 30522],</span>
<span class="hljs-comment">// type: &quot;float32&quot;,</span>
<span class="hljs-comment">// size: 183132,</span>
<span class="hljs-comment">// }</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1scuial"><strong>Example:</strong> Load and run an <code>AutoModelForSeq2SeqLM</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForSeq2SeqLM</span>, <span class="hljs-title class_">AutoTokenizer</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> tokenizer = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoTokenizer</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/t5-small&#x27;</span>);
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForSeq2SeqLM</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/t5-small&#x27;</span>);
<span class="hljs-keyword">const</span> { input_ids } = <span class="hljs-keyword">await</span> <span class="hljs-title function_">tokenizer</span>(<span class="hljs-string">&#x27;translate English to German: I love transformers!&#x27;</span>);
<span class="hljs-keyword">const</span> outputs = <span class="hljs-keyword">await</span> model.<span class="hljs-title function_">generate</span>(input_ids);
<span class="hljs-keyword">const</span> decoded = tokenizer.<span class="hljs-title function_">decode</span>(outputs[<span class="hljs-number">0</span>], { <span class="hljs-attr">skip_special_tokens</span>: <span class="hljs-literal">true</span> });
<span class="hljs-comment">// &#x27;Ich liebe Transformatoren!&#x27;</span><!-- HTML_TAG_END --></pre></div> <h2 class="relative group"><a id="on-this-page" 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="#on-this-page"><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>On this page</span></h2> <p data-svelte-h="svelte-h4f6gu"><strong>Classes</strong><a href="#module_models.AutoModel"><code>AutoModel</code></a> · <a href="#module_models.AutoModelForSequenceClassification"><code>AutoModelForSequenceClassification</code></a> · <a href="#module_models.AutoModelForTokenClassification"><code>AutoModelForTokenClassification</code></a> · <a href="#module_models.AutoModelForSeq2SeqLM"><code>AutoModelForSeq2SeqLM</code></a> · <a href="#module_models.AutoModelForSpeechSeq2Seq"><code>AutoModelForSpeechSeq2Seq</code></a> · <a href="#module_models.AutoModelForTextToSpectrogram"><code>AutoModelForTextToSpectrogram</code></a> · <a href="#module_models.AutoModelForTextToWaveform"><code>AutoModelForTextToWaveform</code></a> · <a href="#module_models.AutoModelForCausalLM"><code>AutoModelForCausalLM</code></a> · <a href="#module_models.AutoModelForMaskedLM"><code>AutoModelForMaskedLM</code></a> · <a href="#module_models.AutoModelForQuestionAnswering"><code>AutoModelForQuestionAnswering</code></a> · <a href="#module_models.AutoModelForVision2Seq"><code>AutoModelForVision2Seq</code></a> · <a href="#module_models.AutoModelForImageClassification"><code>AutoModelForImageClassification</code></a> · <a href="#module_models.AutoModelForImageSegmentation"><code>AutoModelForImageSegmentation</code></a> · <a href="#module_models.AutoModelForSemanticSegmentation"><code>AutoModelForSemanticSegmentation</code></a> · <a href="#module_models.AutoModelForUniversalSegmentation"><code>AutoModelForUniversalSegmentation</code></a> · <a href="#module_models.AutoModelForObjectDetection"><code>AutoModelForObjectDetection</code></a> · <a href="#module_models.AutoModelForZeroShotObjectDetection"><code>AutoModelForZeroShotObjectDetection</code></a> · <a href="#module_models.AutoModelForMaskGeneration"><code>AutoModelForMaskGeneration</code></a> · <a href="#module_models.AutoModelForCTC"><code>AutoModelForCTC</code></a> · <a href="#module_models.AutoModelForAudioClassification"><code>AutoModelForAudioClassification</code></a> · <a href="#module_models.AutoModelForXVector"><code>AutoModelForXVector</code></a> · <a href="#module_models.AutoModelForAudioFrameClassification"><code>AutoModelForAudioFrameClassification</code></a> · <a href="#module_models.AutoModelForDocumentQuestionAnswering"><code>AutoModelForDocumentQuestionAnswering</code></a> · <a href="#module_models.AutoModelForImageMatting"><code>AutoModelForImageMatting</code></a> · <a href="#module_models.AutoModelForImageToImage"><code>AutoModelForImageToImage</code></a> · <a href="#module_models.AutoModelForDepthEstimation"><code>AutoModelForDepthEstimation</code></a> · <a href="#module_models.AutoModelForNormalEstimation"><code>AutoModelForNormalEstimation</code></a> · <a href="#module_models.AutoModelForPoseEstimation"><code>AutoModelForPoseEstimation</code></a> · <a href="#module_models.AutoModelForImageFeatureExtraction"><code>AutoModelForImageFeatureExtraction</code></a> · <a href="#module_models.AutoModelForImageTextToText"><code>AutoModelForImageTextToText</code></a> · <a href="#module_models.AutoModelForAudioTextToText"><code>AutoModelForAudioTextToText</code></a> · <a href="#module_models.PreTrainedModel"><code>PreTrainedModel</code></a></p> <h2 class="relative group"><a id="classes" 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="#classes"><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>Classes</span></h2> <a id="module_models.AutoModel"></a> <h3 class="relative group"><a id="automodel" 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="#automodel"><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>AutoModel</span></h3> <p data-svelte-h="svelte-q5qp30">Helper class which is used to instantiate pretrained models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModel</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModel</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/bert-base-uncased&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForSequenceClassification"></a> <h3 class="relative group"><a id="automodelforsequenceclassification" 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="#automodelforsequenceclassification"><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>AutoModelForSequenceClassification</span></h3> <p data-svelte-h="svelte-v2nlhh">Helper class which is used to instantiate pretrained sequence classification models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForSequenceClassification</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForSequenceClassification</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/distilbert-base-uncased-finetuned-sst-2-english&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForTokenClassification"></a> <h3 class="relative group"><a id="automodelfortokenclassification" 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="#automodelfortokenclassification"><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>AutoModelForTokenClassification</span></h3> <p data-svelte-h="svelte-15xjh1l">Helper class which is used to instantiate pretrained token classification models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForTokenClassification</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForTokenClassification</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/distilbert-base-multilingual-cased-ner-hrl&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForSeq2SeqLM"></a> <h3 class="relative group"><a id="automodelforseq2seqlm" 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="#automodelforseq2seqlm"><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>AutoModelForSeq2SeqLM</span></h3> <p data-svelte-h="svelte-yk78jb">Helper class which is used to instantiate pretrained sequence-to-sequence models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForSeq2SeqLM</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForSeq2SeqLM</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/t5-small&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForSpeechSeq2Seq"></a> <h3 class="relative group"><a id="automodelforspeechseq2seq" 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="#automodelforspeechseq2seq"><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>AutoModelForSpeechSeq2Seq</span></h3> <p data-svelte-h="svelte-d6mudd">Helper class which is used to instantiate pretrained sequence-to-sequence speech-to-text models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForSpeechSeq2Seq</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForSpeechSeq2Seq</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/whisper-tiny.en&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForTextToSpectrogram"></a> <h3 class="relative group"><a id="automodelfortexttospectrogram" 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="#automodelfortexttospectrogram"><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>AutoModelForTextToSpectrogram</span></h3> <p data-svelte-h="svelte-1lbqj3k">Helper class which is used to instantiate pretrained sequence-to-sequence text-to-spectrogram models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForTextToSpectrogram</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForTextToSpectrogram</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/speecht5_tts&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForTextToWaveform"></a> <h3 class="relative group"><a id="automodelfortexttowaveform" 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="#automodelfortexttowaveform"><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>AutoModelForTextToWaveform</span></h3> <p data-svelte-h="svelte-1jj7enf">Helper class which is used to instantiate pretrained text-to-waveform models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForTextToWaveform</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForTextToWaveform</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/mms-tts-eng&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForCausalLM"></a> <h3 class="relative group"><a id="automodelforcausallm" 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="#automodelforcausallm"><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>AutoModelForCausalLM</span></h3> <p data-svelte-h="svelte-2f3a77">Helper class which is used to instantiate pretrained causal language models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForCausalLM</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForCausalLM</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/gpt2&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForMaskedLM"></a> <h3 class="relative group"><a id="automodelformaskedlm" 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="#automodelformaskedlm"><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>AutoModelForMaskedLM</span></h3> <p data-svelte-h="svelte-1vcq7uz">Helper class which is used to instantiate pretrained masked language models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForMaskedLM</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForMaskedLM</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/bert-base-uncased&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForQuestionAnswering"></a> <h3 class="relative group"><a id="automodelforquestionanswering" 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="#automodelforquestionanswering"><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>AutoModelForQuestionAnswering</span></h3> <p data-svelte-h="svelte-uxjsxs">Helper class which is used to instantiate pretrained question answering models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForQuestionAnswering</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForQuestionAnswering</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/distilbert-base-cased-distilled-squad&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForVision2Seq"></a> <h3 class="relative group"><a id="automodelforvision2seq" 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="#automodelforvision2seq"><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>AutoModelForVision2Seq</span></h3> <p data-svelte-h="svelte-45et0e">Helper class which is used to instantiate pretrained vision-to-sequence models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForVision2Seq</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForVision2Seq</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/vit-gpt2-image-captioning&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageClassification"></a> <h3 class="relative group"><a id="automodelforimageclassification" 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="#automodelforimageclassification"><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>AutoModelForImageClassification</span></h3> <p data-svelte-h="svelte-1fqdxll">Helper class which is used to instantiate pretrained image classification models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageClassification</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageClassification</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/vit-base-patch16-224&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageSegmentation"></a> <h3 class="relative group"><a id="automodelforimagesegmentation" 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="#automodelforimagesegmentation"><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>AutoModelForImageSegmentation</span></h3> <p data-svelte-h="svelte-1alzok7">Helper class which is used to instantiate pretrained image segmentation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageSegmentation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageSegmentation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/detr-resnet-50-panoptic&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForSemanticSegmentation"></a> <h3 class="relative group"><a id="automodelforsemanticsegmentation" 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="#automodelforsemanticsegmentation"><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>AutoModelForSemanticSegmentation</span></h3> <p data-svelte-h="svelte-1alzok7">Helper class which is used to instantiate pretrained image segmentation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForSemanticSegmentation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForSemanticSegmentation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/segformer-b0-finetuned-ade-512-512&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForUniversalSegmentation"></a> <h3 class="relative group"><a id="automodelforuniversalsegmentation" 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="#automodelforuniversalsegmentation"><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>AutoModelForUniversalSegmentation</span></h3> <p data-svelte-h="svelte-owk8vg">Helper class which is used to instantiate pretrained universal image segmentation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForUniversalSegmentation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForUniversalSegmentation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/detr-resnet-50-panoptic&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForObjectDetection"></a> <h3 class="relative group"><a id="automodelforobjectdetection" 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="#automodelforobjectdetection"><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>AutoModelForObjectDetection</span></h3> <p data-svelte-h="svelte-73pqau">Helper class which is used to instantiate pretrained object detection models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForObjectDetection</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForObjectDetection</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/detr-resnet-50&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForZeroShotObjectDetection"></a> <h3 class="relative group"><a id="automodelforzeroshotobjectdetection" 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="#automodelforzeroshotobjectdetection"><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>AutoModelForZeroShotObjectDetection</span></h3> <p data-svelte-h="svelte-19nrr8x">Helper class which is used to instantiate pretrained zero-shot object detection models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForZeroShotObjectDetection</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForZeroShotObjectDetection</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/owlvit-base-patch32&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForMaskGeneration"></a> <h3 class="relative group"><a id="automodelformaskgeneration" 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="#automodelformaskgeneration"><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>AutoModelForMaskGeneration</span></h3> <p data-svelte-h="svelte-1jgn1ce">Helper class which is used to instantiate pretrained mask generation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForMaskGeneration</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForMaskGeneration</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/slimsam-77-uniform&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForCTC"></a> <h3 class="relative group"><a id="automodelforctc" 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="#automodelforctc"><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>AutoModelForCTC</span></h3> <p data-svelte-h="svelte-lyqejb">Helper class which is used to instantiate pretrained connectionist temporal classification (CTC) models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForCTC</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForCTC</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/wav2vec2-base-960h&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForAudioClassification"></a> <h3 class="relative group"><a id="automodelforaudioclassification" 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="#automodelforaudioclassification"><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>AutoModelForAudioClassification</span></h3> <p data-svelte-h="svelte-7t8a5o">Helper class which is used to instantiate pretrained audio classification models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForAudioClassification</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForAudioClassification</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/wav2vec2-base-superb-ks&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForXVector"></a> <h3 class="relative group"><a id="automodelforxvector" 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="#automodelforxvector"><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>AutoModelForXVector</span></h3> <p data-svelte-h="svelte-1w5m8pz">Helper class which is used to instantiate pretrained speaker embedding models (X-Vector) with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForXVector</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForXVector</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/wavlm-base-plus-sv&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForAudioFrameClassification"></a> <h3 class="relative group"><a id="automodelforaudioframeclassification" 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="#automodelforaudioframeclassification"><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>AutoModelForAudioFrameClassification</span></h3> <p data-svelte-h="svelte-1wima1r">Helper class which is used to instantiate pretrained audio frame (token) classification models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForAudioFrameClassification</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForAudioFrameClassification</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/pyannote-segmentation-3.0&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForDocumentQuestionAnswering"></a> <h3 class="relative group"><a id="automodelfordocumentquestionanswering" 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="#automodelfordocumentquestionanswering"><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>AutoModelForDocumentQuestionAnswering</span></h3> <p data-svelte-h="svelte-zpnqyz">Helper class which is used to instantiate pretrained document question answering models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForDocumentQuestionAnswering</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForDocumentQuestionAnswering</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/donut-base-finetuned-docvqa&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageMatting"></a> <h3 class="relative group"><a id="automodelforimagematting" 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="#automodelforimagematting"><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>AutoModelForImageMatting</span></h3> <p data-svelte-h="svelte-1wusaux">Helper class which is used to instantiate pretrained image matting models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageMatting</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageMatting</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/vitmatte-small-composition-1k&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageToImage"></a> <h3 class="relative group"><a id="automodelforimagetoimage" 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="#automodelforimagetoimage"><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>AutoModelForImageToImage</span></h3> <p data-svelte-h="svelte-1mfikkf">Helper class which is used to instantiate pretrained image-to-image models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageToImage</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageToImage</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;Xenova/swin2SR-classical-sr-x2-64&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForDepthEstimation"></a> <h3 class="relative group"><a id="automodelfordepthestimation" 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="#automodelfordepthestimation"><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>AutoModelForDepthEstimation</span></h3> <p data-svelte-h="svelte-14nipsa">Helper class which is used to instantiate pretrained depth estimation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForDepthEstimation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForDepthEstimation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/depth-anything-v2-small-ONNX&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForNormalEstimation"></a> <h3 class="relative group"><a id="automodelfornormalestimation" 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="#automodelfornormalestimation"><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>AutoModelForNormalEstimation</span></h3> <p data-svelte-h="svelte-g4p2ho">Helper class which is used to instantiate pretrained surface-normal estimation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForNormalEstimation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForNormalEstimation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/sapiens-normal-0.3b&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForPoseEstimation"></a> <h3 class="relative group"><a id="automodelforposeestimation" 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="#automodelforposeestimation"><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>AutoModelForPoseEstimation</span></h3> <p data-svelte-h="svelte-18e8dxw">Helper class which is used to instantiate pretrained pose estimation models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForPoseEstimation</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForPoseEstimation</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/vitpose-base-simple&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageFeatureExtraction"></a> <h3 class="relative group"><a id="automodelforimagefeatureextraction" 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="#automodelforimagefeatureextraction"><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>AutoModelForImageFeatureExtraction</span></h3> <p data-svelte-h="svelte-1i8912u">Helper class which is used to instantiate pretrained image feature extraction models with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageFeatureExtraction</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageFeatureExtraction</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/dinov3-vits16-pretrain-lvd1689m-ONNX&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForImageTextToText"></a> <h3 class="relative group"><a id="automodelforimagetexttotext" 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="#automodelforimagetexttotext"><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>AutoModelForImageTextToText</span></h3> <p data-svelte-h="svelte-110cxzo">Helper class which is used to instantiate pretrained vision-language models that map images and text to text
(image+text-to-text) with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForImageTextToText</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForImageTextToText</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/LFM2.5-VL-450M-ONNX&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.AutoModelForAudioTextToText"></a> <h3 class="relative group"><a id="automodelforaudiotexttotext" 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="#automodelforaudiotexttotext"><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>AutoModelForAudioTextToText</span></h3> <p data-svelte-h="svelte-uxpcwd">Helper class which is used to instantiate pretrained audio-language models that map audio and text to text
(audio+text-to-text) with the <code>from_pretrained</code> function.</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="language-javascript "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> { <span class="hljs-title class_">AutoModelForAudioTextToText</span> } <span class="hljs-keyword">from</span> <span class="hljs-string">&#x27;@huggingface/transformers&#x27;</span>;
<span class="hljs-keyword">const</span> model = <span class="hljs-keyword">await</span> <span class="hljs-title class_">AutoModelForAudioTextToText</span>.<span class="hljs-title function_">from_pretrained</span>(<span class="hljs-string">&#x27;onnx-community/Voxtral-Mini-4B-Realtime-2602-ONNX&#x27;</span>);<!-- HTML_TAG_END --></pre></div> <a id="module_models.PreTrainedModel"></a> <h3 class="relative group"><a id="pretrainedmodel" 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="#pretrainedmodel"><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>PreTrainedModel</span></h3> <p data-svelte-h="svelte-17fegh5">A base class for pretrained models that provides the model configuration and inference sessions.</p> <a id="module_models.PreTrainedModel.call"></a> <h4 class="relative group"><a id="pretrainedmodelmodelinputs" 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="#pretrainedmodelmodelinputs"><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>PreTrainedModel(model_inputs)</span></h4> <p data-svelte-h="svelte-kzqr29">Runs the model with the provided inputs.</p> <p data-svelte-h="svelte-11fqvcp"><strong>Parameters</strong></p> <ul data-svelte-h="svelte-1ay7wjd"><li><code>model_inputs</code> (<code>Object</code>) — Object containing input tensors.</li></ul> <p data-svelte-h="svelte-g37euu"><strong>Returns:</strong> <code>Promise</code>&lt;<code>Object</code>&gt; — Object containing output tensors.</p> <a id="module_models.PreTrainedModel.constructor"></a> <h4 class="relative group"><a id="pretrainedmodelconstructorconfig-sessions-configs" 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="#pretrainedmodelconstructorconfig-sessions-configs"><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>PreTrainedModel.constructor(config, sessions, configs)</span></h4> <p data-svelte-h="svelte-1l9ohkn">Create a model from configuration and inference sessions.</p> <p data-svelte-h="svelte-11fqvcp"><strong>Parameters</strong></p> <ul data-svelte-h="svelte-opm49v"><li><code>config</code> (<a href="./configs#module_configs.PretrainedConfig"><code>PretrainedConfig</code></a>) — The model configuration.</li> <li><code>sessions</code> (<code>Record</code>&lt;<code>string</code>, <code>any</code>&gt;) — The inference sessions for the model.</li> <li><code>configs</code> (<code>Record</code>&lt;<code>string</code>, <code>Object</code>&gt;) — Additional configuration files (e.g., generation_config.json).</li></ul> <a id="module_models.PreTrainedModel.dispose"></a> <h4 class="relative group"><a id="pretrainedmodeldispose" 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="#pretrainedmodeldispose"><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>PreTrainedModel.dispose()</span></h4> <p data-svelte-h="svelte-1al82ot">Disposes of all the ONNX sessions that were created during inference.</p> <p data-svelte-h="svelte-47an3q"><strong>Returns:</strong> <code>Promise</code>&lt;<code>void[]</code>&gt; — Resolves after each session has been released.</p> <a id="module_models.PreTrainedModel.from_pretrained"></a> <h4 class="relative group"><a id="pretrainedmodelfrompretrainedpretrainedmodelnameorpath-options" 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="#pretrainedmodelfrompretrainedpretrainedmodelnameorpath-options"><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>PreTrainedModel.from_pretrained(pretrained_model_name_or_path, options)</span></h4> <p data-svelte-h="svelte-rpplf6">Instantiate one of the model classes of the library from a pretrained model.</p> <p data-svelte-h="svelte-15wfnsz">The model class to instantiate is selected based on the <code>model_type</code> property of the config object
(either passed as an argument or loaded from <code>pretrained_model_name_or_path</code> if possible)</p> <p data-svelte-h="svelte-11fqvcp"><strong>Parameters</strong></p> <ul data-svelte-h="svelte-11bx1dm"><li><code>pretrained_model_name_or_path</code> (<code>string</code>) — The name or path of the pretrained model. Can be either:
<ul><li>A string, the <em>model ID</em> of a pretrained model hosted inside a model repo on huggingface.co.
Valid model IDs can be located at the root level, like <code>bert-base-uncased</code>, or namespaced under a
user or organization name, like <code>dbmdz/bert-base-german-cased</code>.</li> <li>A path to a <em>directory</em> containing model weights, e.g., <code>./my_model_directory/</code>.</li></ul></li> <li><code>options</code> (<a href="./utils/hub#module_utils/hub.PretrainedModelOptions"><code>PretrainedModelOptions</code></a>) — Additional options for loading the model.</li></ul> <p data-svelte-h="svelte-uwckmf"><strong>Returns:</strong> <code>Promise</code>&lt;<a href="./models#module_models.PreTrainedModel"><code>PreTrainedModel</code></a>&gt; — A model instance with ready inference sessions.</p> <a id="module_models.PreTrainedModel.forward"></a> <h4 class="relative group"><a id="pretrainedmodelforwardmodelinputs" 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="#pretrainedmodelforwardmodelinputs"><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>PreTrainedModel.forward(model_inputs)</span></h4> <p data-svelte-h="svelte-zk6kyf">Run the model’s forward pass.</p> <p data-svelte-h="svelte-11fqvcp"><strong>Parameters</strong></p> <ul data-svelte-h="svelte-gyueul"><li><code>model_inputs</code> (<code>Object</code>) — The input data to the model in the format specified in the ONNX model.</li></ul> <p data-svelte-h="svelte-1ow1cd"><strong>Returns:</strong> <code>Promise</code>&lt;<code>Object</code>&gt; — The output data from the model in the format specified in the ONNX model.</p> <h4 class="relative group"><a id="pretrainedmodelgenerationconfig" 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="#pretrainedmodelgenerationconfig"><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>PreTrainedModel.generation_config</span></h4> <p data-svelte-h="svelte-1zra08">Get the model’s generation config, if it exists.</p> <a id="module_models.PreTrainedModel.generate"></a> <h4 class="relative group"><a id="pretrainedmodelgenerateoptions" 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="#pretrainedmodelgenerateoptions"><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>PreTrainedModel.generate(options)</span></h4> <p data-svelte-h="svelte-1b2w4dp">Generate token sequences with a language-modeling head.</p> <p data-svelte-h="svelte-11fqvcp"><strong>Parameters</strong></p> <ul data-svelte-h="svelte-1hs15oa"><li><code>options</code> (<a href="./generation/parameters#module_generation/parameters.GenerationFunctionParameters"><code>GenerationFunctionParameters</code></a>)</li></ul> <p data-svelte-h="svelte-q05rsi"><strong>Returns:</strong> <code>Promise</code>&lt;<code>ModelOutput</code> | <a href="./utils/tensor#module_utils/tensor.Tensor"><code>Tensor</code></a>&gt; — The output of the model, which can contain the generated token ids, attentions, and scores.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers.js/blob/main/packages/transformers/docs/source/api/models.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_1t06csc = {
assets: "/docs/transformers.js/pr_1665/en",
base: "/docs/transformers.js/pr_1665/en",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/transformers.js/pr_1665/en/_app/immutable/entry/start.cb58eb6f.js"),
import("/docs/transformers.js/pr_1665/en/_app/immutable/entry/app.9eafcf9d.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 11],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
140 kB
·
Xet hash:
8d8ba96618b1c7035e535d6033bd6ca8c7522e6027ad839d0f559e68efa505fc

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