Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Usando os Tokenizers do 🤗 Tokenizers","local":"usando-os-tokenizers-do--tokenizers","sections":[{"title":"Carregando diretamente de um objeto tokenizer","local":"carregando-diretamente-de-um-objeto-tokenizer","sections":[],"depth":2},{"title":"Carregando de um arquivo JSON","local":"carregando-de-um-arquivo-json","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/transformers/main/pt/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/entry/start.3b004bd3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/scheduler.d586627e.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/singletons.0d7813b8.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/index.b0d7e1f3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/paths.183a9cf3.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/entry/app.1f3cbd74.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/index.8589a59c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/nodes/0.30b661ad.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/nodes/6.7c9cb7be.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/CodeBlock.47c46d2c.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/EditOnGithub.073dfa26.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Usando os Tokenizers do 🤗 Tokenizers","local":"usando-os-tokenizers-do--tokenizers","sections":[{"title":"Carregando diretamente de um objeto tokenizer","local":"carregando-diretamente-de-um-objeto-tokenizer","sections":[],"depth":2},{"title":"Carregando de um arquivo JSON","local":"carregando-de-um-arquivo-json","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="usando-os-tokenizers-do--tokenizers" 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="#usando-os-tokenizers-do--tokenizers"><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>Usando os Tokenizers do 🤗 Tokenizers</span></h1> <p data-svelte-h="svelte-borl69">O <code>PreTrainedTokenizerFast</code> depende da biblioteca <a href="https://huggingface.co/docs/tokenizers" rel="nofollow">🤗 Tokenizers</a>. O Tokenizer obtido da biblioteca 🤗 Tokenizers pode ser carregado facilmente pelo 🤗 Transformers.</p> <p data-svelte-h="svelte-1q50rcm">Antes de entrar nos detalhes, vamos começar criando um tokenizer fictício em algumas linhas:</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-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> Tokenizer | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.models <span class="hljs-keyword">import</span> BPE | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.trainers <span class="hljs-keyword">import</span> BpeTrainer | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.pre_tokenizers <span class="hljs-keyword">import</span> Whitespace | |
| <span class="hljs-meta">>>> </span>tokenizer = Tokenizer(BPE(unk_token=<span class="hljs-string">"[UNK]"</span>)) | |
| <span class="hljs-meta">>>> </span>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>]) | |
| <span class="hljs-meta">>>> </span>tokenizer.pre_tokenizer = Whitespace() | |
| <span class="hljs-meta">>>> </span>files = [...] | |
| <span class="hljs-meta">>>> </span>tokenizer.train(files, trainer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17y7lov">Agora temos um tokenizer treinado nos arquivos que foram definidos. Nós podemos continuar usando nessa execução ou salvar em um arquivo JSON para re-utilizar no futuro.</p> <h2 class="relative group"><a id="carregando-diretamente-de-um-objeto-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="#carregando-diretamente-de-um-objeto-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>Carregando diretamente de um objeto tokenizer</span></h2> <p data-svelte-h="svelte-11rm4tu">Vamos ver como aproveitar esse objeto tokenizer na biblioteca 🤗 Transformers. A classe <code>PreTrainedTokenizerFast</code> permite uma instanciação fácil, aceitando o objeto <em>tokenizer</em> instanciado como um argumento:</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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> PreTrainedTokenizerFast | |
| <span class="hljs-meta">>>> </span>fast_tokenizer = PreTrainedTokenizerFast(tokenizer_object=tokenizer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-bzpmh">Esse objeto pode ser utilizado com todos os métodos compartilhados pelos tokenizers dos 🤗 Transformers! Vá para <a href="main_classes/tokenizer">a página do tokenizer</a> para mais informações.</p> <h2 class="relative group"><a id="carregando-de-um-arquivo-json" 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="#carregando-de-um-arquivo-json"><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>Carregando de um arquivo JSON</span></h2> <p data-svelte-h="svelte-vycu7g">Para carregar um tokenizer de um arquivo JSON vamos primeiro começar salvando nosso 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-meta">>>> </span>tokenizer.save(<span class="hljs-string">"tokenizer.json"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-15so4os">A pasta para qual salvamos esse arquivo pode ser passada para o método de inicialização do <code>PreTrainedTokenizerFast</code> usando o <code>tokenizer_file</code> parâmetro:</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-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> PreTrainedTokenizerFast | |
| <span class="hljs-meta">>>> </span>fast_tokenizer = PreTrainedTokenizerFast(tokenizer_file=<span class="hljs-string">"tokenizer.json"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-bzpmh">Esse objeto pode ser utilizado com todos os métodos compartilhados pelos tokenizers dos 🤗 Transformers! Vá para <a href="main_classes/tokenizer">a página do tokenizer</a> para mais informações.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/pt/fast_tokenizers.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p> | |
| <script> | |
| { | |
| __sveltekit_1jqvrjl = { | |
| assets: "/docs/transformers/main/pt", | |
| base: "/docs/transformers/main/pt", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/transformers/main/pt/_app/immutable/entry/start.3b004bd3.js"), | |
| import("/docs/transformers/main/pt/_app/immutable/entry/app.1f3cbd74.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 6], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 15.7 kB
- Xet hash:
- c2f878480764d283c99414ab1028c62b0d118edac417285829821a0409e1a8fa
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.