Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Quicktour","local":"quicktour","sections":[{"title":"Build a tokenizer from scratch","local":"build-a-tokenizer-from-scratch","sections":[{"title":"Training the tokenizer","local":"training-the-tokenizer","sections":[],"depth":3},{"title":"Using the tokenizer","local":"using-the-tokenizer","sections":[],"depth":3},{"title":"Post-processing","local":"post-processing","sections":[],"depth":3},{"title":"Encoding multiple sentences in a batch","local":"encoding-multiple-sentences-in-a-batch","sections":[],"depth":3}],"depth":2},{"title":"Pretrained","local":"pretrained","sections":[{"title":"Using a pretrained tokenizer","local":"using-a-pretrained-tokenizer","sections":[],"depth":3},{"title":"Importing a pretrained tokenizer from legacy vocabulary files","local":"importing-a-pretrained-tokenizer-from-legacy-vocabulary-files","sections":[],"depth":3}],"depth":2}],"depth":1}"> | |
| <link href="/docs/tokenizers/pr_2012/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/entry/start.82c81cf3.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/scheduler.7c59faff.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/singletons.48f81268.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/index.adabef24.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/paths.7e5a9ab3.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/entry/app.cac551ee.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/preload-helper.cd69f041.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/index.09bb5655.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/nodes/0.5c29e5da.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/nodes/18.0cf88216.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/Tip.25c348e8.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.0ba496c3.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/CodeBlock.59939b10.js"> | |
| <link rel="modulepreload" href="/docs/tokenizers/pr_2012/en/_app/immutable/chunks/TokenizersLanguageContent.0fc17a7a.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Quicktour","local":"quicktour","sections":[{"title":"Build a tokenizer from scratch","local":"build-a-tokenizer-from-scratch","sections":[{"title":"Training the tokenizer","local":"training-the-tokenizer","sections":[],"depth":3},{"title":"Using the tokenizer","local":"using-the-tokenizer","sections":[],"depth":3},{"title":"Post-processing","local":"post-processing","sections":[],"depth":3},{"title":"Encoding multiple sentences in a batch","local":"encoding-multiple-sentences-in-a-batch","sections":[],"depth":3}],"depth":2},{"title":"Pretrained","local":"pretrained","sections":[{"title":"Using a pretrained tokenizer","local":"using-a-pretrained-tokenizer","sections":[],"depth":3},{"title":"Importing a pretrained tokenizer from legacy vocabulary files","local":"importing-a-pretrained-tokenizer-from-legacy-vocabulary-files","sections":[],"depth":3}],"depth":2}],"depth":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="quicktour" 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="#quicktour"><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>Quicktour</span></h1> <p data-svelte-h="svelte-vlsd60">Let’s have a quick look at the 🤗 Tokenizers library features. The | |
| library provides an implementation of today’s most used tokenizers that | |
| is both easy to use and blazing fast.</p> <h2 class="relative group"><a id="build-a-tokenizer-from-scratch" 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="#build-a-tokenizer-from-scratch"><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>Build a tokenizer from scratch</span></h2> <p data-svelte-h="svelte-19m2g44">To illustrate how fast the 🤗 Tokenizers library is, let’s train a new | |
| tokenizer on <a href="https://www.salesforce.com/blog/the-wikitext-long-term-dependency-language-modeling-dataset/" rel="nofollow">wikitext-103</a> | |
| (516M of text) in just a few seconds. First things first, you will need | |
| to download this dataset and unzip it with:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->wget https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-raw-v1.zip | |
| unzip wikitext-103-raw-v1.zip<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="training-the-tokenizer" 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="#training-the-tokenizer"><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>Training the tokenizer</span></h3> <p data-svelte-h="svelte-1ab5uuh">In this tour, we will build and train a Byte-Pair Encoding (BPE) | |
| tokenizer. For more information about the different type of tokenizers, | |
| check out this <a href="https://huggingface.co/transformers/tokenizer_summary.html" rel="nofollow">guide</a> in | |
| the 🤗 Transformers documentation. Here, training the tokenizer means it | |
| will learn merge rules by:</p> <ul data-svelte-h="svelte-wkiawp"><li>Start with all the characters present in the training corpus as | |
| tokens.</li> <li>Identify the most common pair of tokens and merge it into one token.</li> <li>Repeat until the vocabulary (e.g., the number of tokens) has reached | |
| the size we want.</li></ul> <p data-svelte-h="svelte-8jg8u0">The main API of the library is the <code>class</code> <code>Tokenizer</code>, here is how | |
| we instantiate one with a BPE model:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> Tokenizer | |
| <span class="hljs-keyword">from</span> tokenizers.models <span class="hljs-keyword">import</span> BPE | |
| tokenizer = Tokenizer(BPE(unk_token=<span class="hljs-string">"[UNK]"</span>))<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-207jr3">To train our tokenizer on the wikitext files, we will need to | |
| instantiate a [trainer]{.title-ref}, in this case a | |
| <code>BpeTrainer</code></p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers.trainers <span class="hljs-keyword">import</span> BpeTrainer | |
| trainer = BpeTrainer(special_tokens=[<span class="hljs-string">"[UNK]"</span>, <span class="hljs-string">"[CLS]"</span>, <span class="hljs-string">"[SEP]"</span>, <span class="hljs-string">"[PAD]"</span>, <span class="hljs-string">"[MASK]"</span>])<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-1t3zo19">We can set the training arguments like <code>vocab_size</code> or <code>min_frequency</code> (here | |
| left at their default values of 30,000 and 0) but the most important | |
| part is to give the <code>special_tokens</code> we | |
| plan to use later on (they are not used at all during training) so that | |
| they get inserted in the vocabulary.</p> <blockquote class="tip"><p data-svelte-h="svelte-a3tvl4">The order in which you write the special tokens list matters: here <code>"[UNK]"</code> will get the ID 0, | |
| <code>"[CLS]"</code> will get the ID 1 and so forth.</p></blockquote> <p data-svelte-h="svelte-142dtc3">We could train our tokenizer right now, but it wouldn’t be optimal. | |
| Without a pre-tokenizer that will split our inputs into words, we might | |
| get tokens that overlap several words: for instance we could get an | |
| <code>"it is"</code> token since those two words | |
| often appear next to each other. Using a pre-tokenizer will ensure no | |
| token is bigger than a word returned by the pre-tokenizer. Here we want | |
| to train a subword BPE tokenizer, and we will use the easiest | |
| pre-tokenizer possible by splitting on whitespace.</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers.pre_tokenizers <span class="hljs-keyword">import</span> Whitespace | |
| tokenizer.pre_tokenizer = Whitespace()<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-1kti9us">Now, we can just call the <code>Tokenizer.train</code> method with any list of files we want to use:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->files = [<span class="hljs-string">f"data/wikitext-103-raw/wiki.<span class="hljs-subst">{split}</span>.raw"</span> <span class="hljs-keyword">for</span> split <span class="hljs-keyword">in</span> [<span class="hljs-string">"test"</span>, <span class="hljs-string">"train"</span>, <span class="hljs-string">"valid"</span>]] | |
| tokenizer.train(files, trainer)<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-ghl0s0">This should only take a few seconds to train our tokenizer on the full | |
| wikitext dataset! To save the tokenizer in one file that contains all | |
| its configuration and vocabulary, just use the | |
| <code>Tokenizer.save</code> method:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer.save(<span class="hljs-string">"data/tokenizer-wiki.json"</span>)<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-18twg3e">and you can reload your tokenizer from that file with the | |
| <code>Tokenizer.from_file</code> <code>classmethod</code>:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer = Tokenizer.from_file(<span class="hljs-string">"data/tokenizer-wiki.json"</span>)<!-- HTML_TAG_END --></pre></div> </div> <h3 class="relative group"><a id="using-the-tokenizer" 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="#using-the-tokenizer"><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>Using the tokenizer</span></h3> <p data-svelte-h="svelte-g8al98">Now that we have trained a tokenizer, we can use it on any text we want | |
| with the <code>Tokenizer.encode</code> method:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode(<span class="hljs-string">"Hello, y'all! How are you 😁 ?"</span>)<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-1eot2u1">This applied the full pipeline of the tokenizer on the text, returning | |
| an <code>Encoding</code> object. To learn more | |
| about this pipeline, and how to apply (or customize) parts of it, check out <a href="https://github.com/huggingface/tokenizers/blob/main/docs/source-doc-builder/pipeline.mdx" rel="nofollow">this page</a>.</p> <p data-svelte-h="svelte-1me9v9l">This <code>Encoding</code> object then has all the | |
| attributes you need for your deep learning model (or other). The | |
| <code>tokens</code> attribute contains the | |
| segmentation of your text in tokens:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">print</span>(output.tokens) | |
| <span class="hljs-comment"># ["Hello", ",", "y", "'", "all", "!", "How", "are", "you", "[UNK]", "?"]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-19hwcs8">Similarly, the <code>ids</code> attribute will | |
| contain the index of each of those tokens in the tokenizer’s | |
| vocabulary:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">print</span>(output.ids) | |
| <span class="hljs-comment"># [27253, 16, 93, 11, 5097, 5, 7961, 5112, 6218, 0, 35]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-oo2v9g">An important feature of the 🤗 Tokenizers library is that it comes with | |
| full alignment tracking, meaning you can always get the part of your | |
| original sentence that corresponds to a given token. Those are stored in | |
| the <code>offsets</code> attribute of our | |
| <code>Encoding</code> object. For instance, let’s | |
| assume we would want to find back what caused the | |
| <code>"[UNK]"</code> token to appear, which is the | |
| token at index 9 in the list, we can just ask for the offset at the | |
| index:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">print</span>(output.offsets[<span class="hljs-number">9</span>]) | |
| <span class="hljs-comment"># (26, 27)</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-295h1u">and those are the indices that correspond to the emoji in the original | |
| sentence:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->sentence = <span class="hljs-string">"Hello, y'all! How are you 😁 ?"</span> | |
| sentence[<span class="hljs-number">26</span>:<span class="hljs-number">27</span>] | |
| <span class="hljs-comment"># "😁"</span><!-- HTML_TAG_END --></pre></div> </div> <h3 class="relative group"><a id="post-processing" 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="#post-processing"><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>Post-processing</span></h3> <p data-svelte-h="svelte-1lt0plb">We might want our tokenizer to automatically add special tokens, like | |
| <code>"[CLS]"</code> or <code>"[SEP]"</code>. To do this, we use a post-processor. | |
| <code>TemplateProcessing</code> is the most | |
| commonly used, you just have to specify a template for the processing of | |
| single sentences and pairs of sentences, along with the special tokens | |
| and their IDs.</p> <p data-svelte-h="svelte-1p6rfjx">When we built our tokenizer, we set <code>"[CLS]"</code> and <code>"[SEP]"</code> in positions 1 | |
| and 2 of our list of special tokens, so this should be their IDs. To | |
| double-check, we can use the <code>Tokenizer.token_to_id</code> method:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer.token_to_id(<span class="hljs-string">"[SEP]"</span>) | |
| <span class="hljs-comment"># 2</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-10p2x7x">Here is how we can set the post-processing to give us the traditional | |
| BERT inputs:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers.processors <span class="hljs-keyword">import</span> TemplateProcessing | |
| tokenizer.post_processor = TemplateProcessing( | |
| single=<span class="hljs-string">"[CLS] $A [SEP]"</span>, | |
| pair=<span class="hljs-string">"[CLS] $A [SEP] $B:1 [SEP]:1"</span>, | |
| special_tokens=[ | |
| (<span class="hljs-string">"[CLS]"</span>, tokenizer.token_to_id(<span class="hljs-string">"[CLS]"</span>)), | |
| (<span class="hljs-string">"[SEP]"</span>, tokenizer.token_to_id(<span class="hljs-string">"[SEP]"</span>)), | |
| ], | |
| )<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-1654s0j">Let’s go over this snippet of code in more details. First we specify | |
| the template for single sentences: those should have the form | |
| <code>"[CLS] $A [SEP]"</code> where | |
| <code>$A</code> represents our sentence.</p> <p data-svelte-h="svelte-1he2eh8">Then, we specify the template for sentence pairs, which should have the | |
| form <code>"[CLS] $A [SEP] $B [SEP]"</code> where | |
| <code>$A</code> represents the first sentence and | |
| <code>$B</code> the second one. The | |
| <code>:1</code> added in the template represent the <code>type IDs</code> we want for each part of our input: it defaults | |
| to 0 for everything (which is why we don’t have | |
| <code>$A:0</code>) and here we set it to 1 for the | |
| tokens of the second sentence and the last <code>"[SEP]"</code> token.</p> <p data-svelte-h="svelte-nbhw3c">Lastly, we specify the special tokens we used and their IDs in our | |
| tokenizer’s vocabulary.</p> <p data-svelte-h="svelte-bh0by8">To check out this worked properly, let’s try to encode the same | |
| sentence as before:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode(<span class="hljs-string">"Hello, y'all! How are you 😁 ?"</span>) | |
| <span class="hljs-built_in">print</span>(output.tokens) | |
| <span class="hljs-comment"># ["[CLS]", "Hello", ",", "y", "'", "all", "!", "How", "are", "you", "[UNK]", "?", "[SEP]"]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-zo3plm">To check the results on a pair of sentences, we just pass the two | |
| sentences to <code>Tokenizer.encode</code>:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode(<span class="hljs-string">"Hello, y'all!"</span>, <span class="hljs-string">"How are you 😁 ?"</span>) | |
| <span class="hljs-built_in">print</span>(output.tokens) | |
| <span class="hljs-comment"># ["[CLS]", "Hello", ",", "y", "'", "all", "!", "[SEP]", "How", "are", "you", "[UNK]", "?", "[SEP]"]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-14y4jd4">You can then check the type IDs attributed to each token is correct with</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">print</span>(output.type_ids) | |
| <span class="hljs-comment"># [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-sq2861">If you save your tokenizer with <code>Tokenizer.save</code>, the post-processor will be saved along.</p> <h3 class="relative group"><a id="encoding-multiple-sentences-in-a-batch" 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="#encoding-multiple-sentences-in-a-batch"><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>Encoding multiple sentences in a batch</span></h3> <p data-svelte-h="svelte-1iibqnx">To get the full speed of the 🤗 Tokenizers library, it’s best to | |
| process your texts by batches by using the | |
| <code>Tokenizer.encode_batch</code> method:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode_batch([<span class="hljs-string">"Hello, y'all!"</span>, <span class="hljs-string">"How are you 😁 ?"</span>])<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-ipm28y">The output is then a list of <code>Encoding</code> | |
| objects like the ones we saw before. You can process together as many | |
| texts as you like, as long as it fits in memory.</p> <p data-svelte-h="svelte-3bcocl">To process a batch of sentences pairs, pass two lists to the | |
| <code>Tokenizer.encode_batch</code> method: the | |
| list of sentences A and the list of sentences B:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode_batch( | |
| [[<span class="hljs-string">"Hello, y'all!"</span>, <span class="hljs-string">"How are you 😁 ?"</span>], [<span class="hljs-string">"Hello to you too!"</span>, <span class="hljs-string">"I'm fine, thank you!"</span>]] | |
| )<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-136mrhv">When encoding multiple sentences, you can automatically pad the outputs | |
| to the longest sentence present by using | |
| <code>Tokenizer.enable_padding</code>, with the | |
| <code>pad_token</code> and its ID (which we can | |
| double-check the id for the padding token with | |
| <code>Tokenizer.token_to_id</code> like before):</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->tokenizer.enable_padding(pad_id=<span class="hljs-number">3</span>, pad_token=<span class="hljs-string">"[PAD]"</span>)<!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-ljzkee">We can set the <code>direction</code> of the padding | |
| (defaults to the right) or a given <code>length</code> if we want to pad every sample to that specific number (here | |
| we leave it unset to pad to the size of the longest text).</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->output = tokenizer.encode_batch([<span class="hljs-string">"Hello, y'all!"</span>, <span class="hljs-string">"How are you 😁 ?"</span>]) | |
| <span class="hljs-built_in">print</span>(output[<span class="hljs-number">1</span>].tokens) | |
| <span class="hljs-comment"># ["[CLS]", "How", "are", "you", "[UNK]", "?", "[SEP]", "[PAD]"]</span><!-- HTML_TAG_END --></pre></div> </div> <p data-svelte-h="svelte-e366mm">In this case, the <code>attention mask</code> generated by the | |
| tokenizer takes the padding into account:</p> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">print</span>(output[<span class="hljs-number">1</span>].attention_mask) | |
| <span class="hljs-comment"># [1, 1, 1, 1, 1, 1, 1, 0]</span><!-- HTML_TAG_END --></pre></div> </div> <h2 class="relative group"><a id="pretrained" 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="#pretrained"><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>Pretrained</span></h2> <div class="flex space-x-2 items-center my-1.5 mr-8 h-7 !pl-0 -mx-3 md:mx-0"><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd border-gray-800 bg-black dark:bg-gray-700 text-white"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M15.84.5a16.4,16.4,0,0,0-3.57.32C9.1,1.39,8.53,2.53,8.53,4.64V7.48H16v1H5.77a4.73,4.73,0,0,0-4.7,3.74,14.82,14.82,0,0,0,0,7.54c.57,2.28,1.86,3.82,4,3.82h2.6V20.14a4.73,4.73,0,0,1,4.63-4.63h7.38a3.72,3.72,0,0,0,3.73-3.73V4.64A4.16,4.16,0,0,0,19.65.82,20.49,20.49,0,0,0,15.84.5ZM11.78,2.77a1.39,1.39,0,0,1,1.38,1.46,1.37,1.37,0,0,1-1.38,1.38A1.42,1.42,0,0,1,10.4,4.23,1.44,1.44,0,0,1,11.78,2.77Z" fill="#5a9fd4"></path><path d="M16.16,31.5a16.4,16.4,0,0,0,3.57-.32c3.17-.57,3.74-1.71,3.74-3.82V24.52H16v-1H26.23a4.73,4.73,0,0,0,4.7-3.74,14.82,14.82,0,0,0,0-7.54c-.57-2.28-1.86-3.82-4-3.82h-2.6v3.41a4.73,4.73,0,0,1-4.63,4.63H12.35a3.72,3.72,0,0,0-3.73,3.73v7.14a4.16,4.16,0,0,0,3.73,3.82A20.49,20.49,0,0,0,16.16,31.5Zm4.06-2.27a1.39,1.39,0,0,1-1.38-1.46,1.37,1.37,0,0,1,1.38-1.38,1.42,1.42,0,0,1,1.38,1.38A1.44,1.44,0,0,1,20.22,29.23Z" fill="#ffd43b"></path></svg> Python </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" preserveAspectRatio="xMidYMid meet" width="1em" height="1em" viewBox="0 0 32 32"><path d="M31.77,15.61l-1.34-.83c0-.13,0-.26,0-.39l1.16-1.08a.46.46,0,0,0,.14-.43.44.44,0,0,0-.29-.34L29.92,12l-.12-.38.92-1.28a.46.46,0,0,0,.06-.45.47.47,0,0,0-.36-.28l-1.55-.25L28.68,9l.66-1.44a.48.48,0,0,0,0-.45.46.46,0,0,0-.4-.2L27.32,7l-.25-.3.36-1.54a.46.46,0,0,0-.12-.43.46.46,0,0,0-.43-.13l-1.54.37L25,4.68l.06-1.58a.44.44,0,0,0-.21-.4.45.45,0,0,0-.45,0L23,3.32l-.35-.19L22.4,1.57a.46.46,0,0,0-.28-.35.48.48,0,0,0-.45.05l-1.28.92L20,2.08,19.46.6a.44.44,0,0,0-.34-.29.46.46,0,0,0-.43.14L17.62,1.6l-.39,0L16.39.22a.46.46,0,0,0-.78,0l-.83,1.34-.39,0L13.31.45a.46.46,0,0,0-.43-.14.44.44,0,0,0-.34.29L12,2.08l-.38.11-1.28-.92a.48.48,0,0,0-.45-.05.5.5,0,0,0-.28.35L9.35,3.13,9,3.32,7.57,2.66a.45.45,0,0,0-.45,0,.49.49,0,0,0-.21.4L7,4.68l-.31.25L5.13,4.56a.48.48,0,0,0-.44.13.46.46,0,0,0-.12.43l.36,1.54L4.68,7l-1.58,0a.46.46,0,0,0-.4.2.48.48,0,0,0,0,.45L3.32,9l-.19.35L1.57,9.6a.47.47,0,0,0-.35.28.48.48,0,0,0,.05.45l.92,1.28c0,.12-.07.25-.11.38L.6,12.54a.44.44,0,0,0-.29.34.46.46,0,0,0,.14.43L1.6,14.39l0,.39-1.35.83a.47.47,0,0,0,0,.78l1.35.84,0,.39L.45,18.69a.46.46,0,0,0-.14.43.44.44,0,0,0,.29.34L2.08,20c0,.13.07.26.11.39l-.92,1.28a.46.46,0,0,0-.05.44.45.45,0,0,0,.36.28l1.55.25.19.35-.65,1.44a.45.45,0,0,0,.43.65L4.68,25l.25.3-.36,1.54a.46.46,0,0,0,.12.43.48.48,0,0,0,.44.12l1.54-.36.3.25L6.91,28.9a.49.49,0,0,0,.21.4.48.48,0,0,0,.45,0L9,28.68l.35.19.26,1.56a.46.46,0,0,0,.27.35.48.48,0,0,0,.45-.05l1.28-.92.38.12.55,1.47a.47.47,0,0,0,.34.29.46.46,0,0,0,.43-.13l1.08-1.16.39,0,.83,1.34A.46.46,0,0,0,16,32a.47.47,0,0,0,.4-.22l.83-1.34.39,0,1.08,1.16a.46.46,0,0,0,.43.13.47.47,0,0,0,.34-.29L20,29.93l.38-.12,1.28.92a.48.48,0,0,0,.45.05.45.45,0,0,0,.27-.35l.26-1.56.35-.19,1.43.66a.48.48,0,0,0,.45,0,.49.49,0,0,0,.21-.4L25,27.32l.3-.25,1.54.36a.48.48,0,0,0,.44-.12.46.46,0,0,0,.12-.43l-.36-1.54.25-.3,1.58.05a.45.45,0,0,0,.43-.65L28.69,23l.19-.35,1.55-.25a.45.45,0,0,0,.36-.28.43.43,0,0,0-.06-.44l-.92-1.28.12-.39,1.48-.55a.44.44,0,0,0,.29-.34.46.46,0,0,0-.14-.43L30.4,17.62c0-.13,0-.26,0-.39l1.34-.84a.46.46,0,0,0,0-.78Zm-9,11.16A1,1,0,1,1,23.92,26a.95.95,0,0,1-1.14.73Zm-.45-3.09a.87.87,0,0,0-1,.67l-.48,2.22a11.74,11.74,0,0,1-9.75,0l-.48-2.23a.85.85,0,0,0-1-.66l-2,.42a14.67,14.67,0,0,1-1-1.2h9.58c.1,0,.18,0,.18-.12V19.35c0-.1-.08-.12-.18-.12h-2.8V17.08h3a1.9,1.9,0,0,1,1.86,1.62c.12.47.39,2,.57,2.5s.91,1.65,1.69,1.65h4.77l.17,0a11,11,0,0,1-1.08,1.27l-2-.43Zm-13.24,3A.94.94,0,0,1,8,26a1,1,0,1,1,1.13.73ZM5.45,12a1,1,0,0,1-1.74.77,1,1,0,0,1,.49-1.26A1,1,0,0,1,5.45,12ZM4.33,14.66l2.05-.91a.87.87,0,0,0,.44-1.15l-.42-.95H8.06v7.46H4.73a11.37,11.37,0,0,1-.45-3.21,10.41,10.41,0,0,1,.07-1.26Zm9-.73v-2.2h3.95c.2,0,1.44.24,1.44,1.16,0,.77-.95,1-1.73,1H13.32Zm14.34,2q0,.45,0,.87h-1.2c-.12,0-.17.08-.17.2v.55c0,1.3-.73,1.58-1.37,1.65s-1.29-.25-1.37-.63a4.13,4.13,0,0,0-1.91-3.21C22.79,14.59,24,13.49,24,12a3.76,3.76,0,0,0-1.83-3.09,5.22,5.22,0,0,0-2.52-.83H7.25a11.79,11.79,0,0,1,6.54-3.7l1.47,1.54a.87.87,0,0,0,1.22,0l1.64-1.57a11.69,11.69,0,0,1,8,5.72L25,12.64a.87.87,0,0,0,.44,1.14l2.16,1a11.46,11.46,0,0,1,.06,1.17ZM15.25,3.1a1,1,0,0,1,1.34,0,1,1,0,0,1,0,1.35,1,1,0,0,1-1.34,0,1,1,0,0,1,0-1.35Zm11.13,9a.94.94,0,0,1,1.25-.48,1,1,0,1,1-1.25.48Z" fill="currentColor"></path></svg> Rust </div><div class="flex items-center border rounded-lg px-1.5 py-1 leading-none select-none text-smd text-gray-500 cursor-pointer opacity-90 hover:text-gray-700 dark:hover:text-gray-200 hover:shadow-sm"><svg class="mr-1.5" 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 0 256 289"><path fill="#539E43" d="M128 288.464c-3.975 0-7.685-1.06-11.13-2.915l-35.247-20.936c-5.3-2.915-2.65-3.975-1.06-4.505c7.155-2.385 8.48-2.915 15.9-7.156c.796-.53 1.856-.265 2.65.265l27.032 16.166c1.06.53 2.385.53 3.18 0l105.74-61.217c1.06-.53 1.59-1.59 1.59-2.915V83.08c0-1.325-.53-2.385-1.59-2.915l-105.74-60.953c-1.06-.53-2.385-.53-3.18 0L20.405 80.166c-1.06.53-1.59 1.855-1.59 2.915v122.17c0 1.06.53 2.385 1.59 2.915l28.887 16.695c15.636 7.95 25.44-1.325 25.44-10.6V93.68c0-1.59 1.326-3.18 3.181-3.18h13.516c1.59 0 3.18 1.325 3.18 3.18v120.58c0 20.936-11.396 33.126-31.272 33.126c-6.095 0-10.865 0-24.38-6.625l-27.827-15.9C4.24 220.885 0 213.465 0 205.515V83.346C0 75.396 4.24 67.976 11.13 64L116.87 2.783c6.625-3.71 15.635-3.71 22.26 0L244.87 64C251.76 67.975 256 75.395 256 83.346v122.17c0 7.95-4.24 15.37-11.13 19.345L139.13 286.08c-3.445 1.59-7.42 2.385-11.13 2.385Zm32.596-84.009c-46.377 0-55.917-21.2-55.917-39.221c0-1.59 1.325-3.18 3.18-3.18h13.78c1.59 0 2.916 1.06 2.916 2.65c2.12 14.045 8.215 20.936 36.306 20.936c22.261 0 31.802-5.035 31.802-16.96c0-6.891-2.65-11.926-37.367-15.372c-28.886-2.915-46.907-9.275-46.907-32.33c0-21.467 18.02-34.187 48.232-34.187c33.921 0 50.617 11.66 52.737 37.101c0 .795-.265 1.59-.795 2.385c-.53.53-1.325 1.06-2.12 1.06h-13.78c-1.326 0-2.65-1.06-2.916-2.385c-3.18-14.575-11.395-19.345-33.126-19.345c-24.38 0-27.296 8.48-27.296 14.84c0 7.686 3.445 10.07 36.306 14.31c32.597 4.24 47.967 10.336 47.967 33.127c-.265 23.321-19.345 36.571-53.002 36.571Z"></path></svg> Node </div></div> <div class="language-select"> <h3 class="relative group"><a id="using-a-pretrained-tokenizer" 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="#using-a-pretrained-tokenizer"><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>Using a pretrained tokenizer</span></h3> <p data-svelte-h="svelte-dzel7a">You can load any tokenizer from the Hugging Face Hub as long as a | |
| <code>tokenizer.json</code> file is available in the repository.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> Tokenizer | |
| tokenizer = Tokenizer.from_pretrained(<span class="hljs-string">"bert-base-uncased"</span>)<!-- HTML_TAG_END --></pre></div> <h3 class="relative group"><a id="importing-a-pretrained-tokenizer-from-legacy-vocabulary-files" 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="#importing-a-pretrained-tokenizer-from-legacy-vocabulary-files"><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>Importing a pretrained tokenizer from legacy vocabulary files</span></h3> <p data-svelte-h="svelte-8l30n4">You can also import a pretrained tokenizer directly in, as long as you | |
| have its vocabulary file. For instance, here is how to import the | |
| classic pretrained BERT tokenizer:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> BertWordPieceTokenizer | |
| tokenizer = BertWordPieceTokenizer(<span class="hljs-string">"bert-base-uncased-vocab.txt"</span>, lowercase=<span class="hljs-literal">True</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-v74lz7">as long as you have downloaded the file <code>bert-base-uncased-vocab.txt</code> with</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->wget https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt<!-- HTML_TAG_END --></pre></div> </div> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/tokenizers/blob/main/docs/source-doc-builder/quicktour.mdx" 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_1sdq0lx = { | |
| assets: "/docs/tokenizers/pr_2012/en", | |
| base: "/docs/tokenizers/pr_2012/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/tokenizers/pr_2012/en/_app/immutable/entry/start.82c81cf3.js"), | |
| import("/docs/tokenizers/pr_2012/en/_app/immutable/entry/app.cac551ee.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 18], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 216 kB
- Xet hash:
- 951bcdfb9adbb4c9505ddbd3caa5045bd1a5e455f5111bc02a800a97febe02ea
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.