Buckets:
| <meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{"local":"modelos-multilingusticos-para-inferncia","sections":[{"local":"xlm","sections":[{"local":"xlm-com-language-embeddings","title":"XLM com language embeddings"},{"local":"xlm-sem-language-embeddings","title":"XLM sem language embeddings"}],"title":"XLM"},{"local":"bert","title":"BERT"},{"local":"xlmroberta","title":"XLM-RoBERTa"},{"local":"m2m100","title":"M2M100"},{"local":"mbart","title":"MBart"}],"title":"Modelos multilinguísticos para inferência"}" data-svelte="svelte-1phssyn"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/assets/pages/__layout.svelte-hf-doc-builder.css"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/start-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/chunks/vendor-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/chunks/paths-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/pages/__layout.svelte-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/pages/multilingual.mdx-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/chunks/IconCopyLink-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/chunks/CodeBlock-hf-doc-builder.js"> | |
| <link rel="modulepreload" href="/docs/transformers/v4.30.2/pt/_app/chunks/DocNotebookDropdown-hf-doc-builder.js"> | |
| <h1 class="relative group"><a id="modelos-multilingusticos-para-inferncia" 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="#modelos-multilingusticos-para-inferncia"><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>Modelos multilinguísticos para inferência | |
| </span></h1> | |
| <div class="flex space-x-1 absolute z-10 right-0 top-0"> | |
| <div class="relative colab-dropdown "> | |
| <button class=" " type="button"> | |
| <img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"> | |
| </button> | |
| </div> | |
| <div class="relative colab-dropdown "> | |
| <button class=" " type="button"> | |
| <img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"> | |
| </button> | |
| </div></div> | |
| <p>Existem vários modelos multilinguísticos no 🤗 Transformers e seus usos para inferência diferem dos modelos monolíngues. | |
| No entanto, nem <em>todos</em> os usos dos modelos multilíngues são tão diferentes. | |
| Alguns modelos, como o <a href="https://huggingface.co/bert-base-multilingual-uncased" rel="nofollow">bert-base-multilingual-uncased</a>, | |
| podem ser usados como se fossem monolíngues. Este guia irá te ajudar a usar modelos multilíngues cujo uso difere | |
| para o propósito de inferência.</p> | |
| <h2 class="relative group"><a id="xlm" 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="#xlm"><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>XLM | |
| </span></h2> | |
| <p>O XLM tem dez checkpoints diferentes dos quais apenas um é monolíngue. | |
| Os nove checkpoints restantes do modelo são subdivididos em duas categorias: | |
| checkpoints que usam de language embeddings e os que não.</p> | |
| <h3 class="relative group"><a id="xlm-com-language-embeddings" 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="#xlm-com-language-embeddings"><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>XLM com language embeddings | |
| </span></h3> | |
| <p>Os seguintes modelos de XLM usam language embeddings para especificar a linguagem utilizada para a inferência.</p> | |
| <ul><li><code>xlm-mlm-ende-1024</code> (Masked language modeling, English-German)</li> | |
| <li><code>xlm-mlm-enfr-1024</code> (Masked language modeling, English-French)</li> | |
| <li><code>xlm-mlm-enro-1024</code> (Masked language modeling, English-Romanian)</li> | |
| <li><code>xlm-mlm-xnli15-1024</code> (Masked language modeling, XNLI languages)</li> | |
| <li><code>xlm-mlm-tlm-xnli15-1024</code> (Masked language modeling + translation, XNLI languages)</li> | |
| <li><code>xlm-clm-enfr-1024</code> (Causal language modeling, English-French)</li> | |
| <li><code>xlm-clm-ende-1024</code> (Causal language modeling, English-German)</li></ul> | |
| <p>Os language embeddings são representados por um tensor de mesma dimensão que os <code>input_ids</code> passados ao modelo. | |
| Os valores destes tensores dependem do idioma utilizado e se identificam pelos atributos <code>lang2id</code> e <code>id2lang</code> do tokenizador.</p> | |
| <p>Neste exemplo, carregamos o checkpoint <code>xlm-clm-enfr-1024</code>(Causal language modeling, English-French):</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> XLMTokenizer, XLMWithLMHeadModel | |
| <span class="hljs-meta">>>> </span>tokenizer = XLMTokenizer.from_pretrained(<span class="hljs-string">"xlm-clm-enfr-1024"</span>) | |
| <span class="hljs-meta">>>> </span>model = XLMWithLMHeadModel.from_pretrained(<span class="hljs-string">"xlm-clm-enfr-1024"</span>)<!-- HTML_TAG_END --></pre></div> | |
| <p>O atributo <code>lang2id</code> do tokenizador mostra os idiomas deste modelo e seus ids:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-built_in">print</span>(tokenizer.lang2id) | |
| {<span class="hljs-string">'en'</span>: <span class="hljs-number">0</span>, <span class="hljs-string">'fr'</span>: <span class="hljs-number">1</span>}<!-- HTML_TAG_END --></pre></div> | |
| <p>Em seguida, cria-se um input de exemplo:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>input_ids = torch.tensor([tokenizer.encode(<span class="hljs-string">"Wikipedia was used to"</span>)]) <span class="hljs-comment"># batch size of 1</span><!-- HTML_TAG_END --></pre></div> | |
| <p>Estabelece-se o id do idioma, por exemplo <code>"en"</code>, e utiliza-se o mesmo para definir a language embedding. | |
| A language embedding é um tensor preenchido com <code>0</code>, que é o id de idioma para o inglês. | |
| Este tensor deve ser do mesmo tamanho que os <code>input_ids</code>.</p> | |
| <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> | |
| <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> | |
| Copied</div></button></div> | |
| <pre><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>language_id = tokenizer.lang2id[<span class="hljs-string">"en"</span>] <span class="hljs-comment"># 0</span> | |
| <span class="hljs-meta">>>> </span>langs = torch.tensor([language_id] * input_ids.shape[<span class="hljs-number">1</span>]) <span class="hljs-comment"># torch.tensor([0, 0, 0, ..., 0])</span> | |
| <span class="hljs-meta">>>> </span><span class="hljs-comment"># We reshape it to be of size (batch_size, sequence_length)</span> | |
| <span class="hljs-meta">>>> </span>langs = langs.view(<span class="hljs-number">1</span>, -<span class="hljs-number">1</span>) <span class="hljs-comment"># is now of shape [1, sequence_length] (we have a batch size of 1)</span><!-- HTML_TAG_END --></pre></div> | |
| <p>Agora você pode passar os <code>input_ids</code> e a language embedding ao modelo:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>outputs = model(input_ids, langs=langs)<!-- HTML_TAG_END --></pre></div> | |
| <p>O script <a href="https://github.com/huggingface/transformers/tree/master/examples/pytorch/text-generation/run_generation.py" rel="nofollow">run_generation.py</a> pode gerar um texto com language embeddings utilizando os checkpoints <code>xlm-clm</code>.</p> | |
| <h3 class="relative group"><a id="xlm-sem-language-embeddings" 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="#xlm-sem-language-embeddings"><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>XLM sem language embeddings | |
| </span></h3> | |
| <p>Os seguintes modelos XLM não requerem o uso de language embeddings durante a inferência:</p> | |
| <ul><li><code>xlm-mlm-17-1280</code> (Modelagem de linguagem com máscara, 17 idiomas)</li> | |
| <li><code>xlm-mlm-100-1280</code> (Modelagem de linguagem com máscara, 100 idiomas)</li></ul> | |
| <p>Estes modelos são utilizados para representações genéricas de frase diferentemente dos checkpoints XLM anteriores.</p> | |
| <h2 class="relative group"><a id="bert" 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="#bert"><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>BERT | |
| </span></h2> | |
| <p>Os seguintes modelos do BERT podem ser utilizados para tarefas multilinguísticas:</p> | |
| <ul><li><code>bert-base-multilingual-uncased</code> (Modelagem de linguagem com máscara + Previsão de frases, 102 idiomas)</li> | |
| <li><code>bert-base-multilingual-cased</code> (Modelagem de linguagem com máscara + Previsão de frases, 104 idiomas)</li></ul> | |
| <p>Estes modelos não requerem language embeddings durante a inferência. Devem identificar a linguagem a partir | |
| do contexto e realizar a inferência em sequência.</p> | |
| <h2 class="relative group"><a id="xlmroberta" 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="#xlmroberta"><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>XLM-RoBERTa | |
| </span></h2> | |
| <p>Os seguintes modelos do XLM-RoBERTa podem ser utilizados para tarefas multilinguísticas:</p> | |
| <ul><li><code>xlm-roberta-base</code> (Modelagem de linguagem com máscara, 100 idiomas)</li> | |
| <li><code>xlm-roberta-large</code> Modelagem de linguagem com máscara, 100 idiomas)</li></ul> | |
| <p>O XLM-RoBERTa foi treinado com 2,5 TB de dados do CommonCrawl recém-criados e testados em 100 idiomas. | |
| Proporciona fortes vantagens sobre os modelos multilinguísticos publicados anteriormente como o mBERT e o XLM em tarefas | |
| subsequentes como a classificação, a rotulagem de sequências e à respostas a perguntas.</p> | |
| <h2 class="relative group"><a id="m2m100" 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="#m2m100"><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>M2M100 | |
| </span></h2> | |
| <p>Os seguintes modelos de M2M100 podem ser utilizados para traduções multilinguísticas:</p> | |
| <ul><li><code>facebook/m2m100_418M</code> (Tradução)</li> | |
| <li><code>facebook/m2m100_1.2B</code> (Tradução)</li></ul> | |
| <p>Neste exemplo, o checkpoint <code>facebook/m2m100_418M</code> é carregado para traduzir do mandarim ao inglês. É possível | |
| estabelecer o idioma de origem no tokenizador:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> M2M100ForConditionalGeneration, M2M100Tokenizer | |
| <span class="hljs-meta">>>> </span>en_text = <span class="hljs-string">"Do not meddle in the affairs of wizards, for they are subtle and quick to anger."</span> | |
| <span class="hljs-meta">>>> </span>chinese_text = <span class="hljs-string">"不要插手巫師的事務, 因為他們是微妙的, 很快就會發怒."</span> | |
| <span class="hljs-meta">>>> </span>tokenizer = M2M100Tokenizer.from_pretrained(<span class="hljs-string">"facebook/m2m100_418M"</span>, src_lang=<span class="hljs-string">"zh"</span>) | |
| <span class="hljs-meta">>>> </span>model = M2M100ForConditionalGeneration.from_pretrained(<span class="hljs-string">"facebook/m2m100_418M"</span>)<!-- HTML_TAG_END --></pre></div> | |
| <p>Tokenização do texto:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>encoded_zh = tokenizer(chinese_text, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> | |
| <p>O M2M100 força o id do idioma de destino como o primeiro token gerado para traduzir ao idioma de destino. | |
| É definido o <code>forced_bos_token_id</code> como <code>en</code> no método <code>generate</code> para traduzir ao inglês.</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>generated_tokens = model.generate(**encoded_zh, forced_bos_token_id=tokenizer.get_lang_id(<span class="hljs-string">"en"</span>)) | |
| <span class="hljs-meta">>>> </span>tokenizer.batch_decode(generated_tokens, skip_special_tokens=<span class="hljs-literal">True</span>) | |
| <span class="hljs-string">'Do not interfere with the matters of the witches, because they are delicate and will soon be angry.'</span><!-- HTML_TAG_END --></pre></div> | |
| <h2 class="relative group"><a id="mbart" 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="#mbart"><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>MBart | |
| </span></h2> | |
| <p>Os seguintes modelos do MBart podem ser utilizados para tradução multilinguística:</p> | |
| <ul><li><code>facebook/mbart-large-50-one-to-many-mmt</code> (Tradução automática multilinguística de um a vários, 50 idiomas)</li> | |
| <li><code>facebook/mbart-large-50-many-to-many-mmt</code> (Tradução automática multilinguística de vários a vários, 50 idiomas)</li> | |
| <li><code>facebook/mbart-large-50-many-to-one-mmt</code> (Tradução automática multilinguística vários a um, 50 idiomas)</li> | |
| <li><code>facebook/mbart-large-50</code> (Tradução multilinguística, 50 idiomas)</li> | |
| <li><code>facebook/mbart-large-cc25</code></li></ul> | |
| <p>Neste exemplo, carrega-se o checkpoint <code>facebook/mbart-large-50-many-to-many-mmt</code> para traduzir do finlandês ao inglês. | |
| Pode-se definir o idioma de origem no tokenizador:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, AutoModelForSeq2SeqLM | |
| <span class="hljs-meta">>>> </span>en_text = <span class="hljs-string">"Do not meddle in the affairs of wizards, for they are subtle and quick to anger."</span> | |
| <span class="hljs-meta">>>> </span>fi_text = <span class="hljs-string">"Älä sekaannu velhojen asioihin, sillä ne ovat hienovaraisia ja nopeasti vihaisia."</span> | |
| <span class="hljs-meta">>>> </span>tokenizer = AutoTokenizer.from_pretrained(<span class="hljs-string">"facebook/mbart-large-50-many-to-many-mmt"</span>, src_lang=<span class="hljs-string">"fi_FI"</span>) | |
| <span class="hljs-meta">>>> </span>model = AutoModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">"facebook/mbart-large-50-many-to-many-mmt"</span>)<!-- HTML_TAG_END --></pre></div> | |
| <p>Tokenizando o texto:</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>encoded_en = tokenizer(en_text, return_tensors=<span class="hljs-string">"pt"</span>)<!-- HTML_TAG_END --></pre></div> | |
| <p>O MBart força o id do idioma de destino como o primeiro token gerado para traduzir ao idioma de destino. | |
| É definido o <code>forced_bos_token_id</code> como <code>en</code> no método <code>generate</code> para traduzir ao inglês.</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><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>generated_tokens = model.generate(**encoded_en, forced_bos_token_id=tokenizer.lang_code_to_id(<span class="hljs-string">"en_XX"</span>)) | |
| <span class="hljs-meta">>>> </span>tokenizer.batch_decode(generated_tokens, skip_special_tokens=<span class="hljs-literal">True</span>) | |
| <span class="hljs-string">"Don't interfere with the wizard's affairs, because they are subtle, will soon get angry."</span><!-- HTML_TAG_END --></pre></div> | |
| <p>Se estiver usando o checkpoint <code>facebook/mbart-large-50-many-to-one-mmt</code> não será necessário forçar o id do idioma de destino | |
| como sendo o primeiro token generado, caso contrário a usagem é a mesma.</p> | |
| <script type="module" data-hydrate="v20liu"> | |
| import { start } from "/docs/transformers/v4.30.2/pt/_app/start-hf-doc-builder.js"; | |
| start({ | |
| target: document.querySelector('[data-hydrate="v20liu"]').parentNode, | |
| paths: {"base":"/docs/transformers/v4.30.2/pt","assets":"/docs/transformers/v4.30.2/pt"}, | |
| session: {}, | |
| route: false, | |
| spa: false, | |
| trailing_slash: "never", | |
| hydrate: { | |
| status: 200, | |
| error: null, | |
| nodes: [ | |
| import("/docs/transformers/v4.30.2/pt/_app/pages/__layout.svelte-hf-doc-builder.js"), | |
| import("/docs/transformers/v4.30.2/pt/_app/pages/multilingual.mdx-hf-doc-builder.js") | |
| ], | |
| params: {} | |
| } | |
| }); | |
| </script> | |
Xet Storage Details
- Size:
- 36.3 kB
- Xet hash:
- fdc546e4c7ecb4362a181f0d3bdfe4760fb0f4a0158b90a9de8300c94f5341ed
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.