Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Modelos multilinguísticos para inferência","local":"modelos-multilinguísticos-para-inferência","sections":[{"title":"XLM","local":"xlm","sections":[{"title":"XLM com language embeddings","local":"xlm-com-language-embeddings","sections":[],"depth":3},{"title":"XLM sem language embeddings","local":"xlm-sem-language-embeddings","sections":[],"depth":3}],"depth":2},{"title":"BERT","local":"bert","sections":[],"depth":2},{"title":"XLM-RoBERTa","local":"xlm-roberta","sections":[],"depth":2},{"title":"M2M100","local":"m2m100","sections":[],"depth":2},{"title":"MBart","local":"mbart","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/9.e1016721.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/DocNotebookDropdown.43d2c946.js"> | |
| <link rel="modulepreload" href="/docs/transformers/main/pt/_app/immutable/chunks/globals.7f7f1b26.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":"Modelos multilinguísticos para inferência","local":"modelos-multilinguísticos-para-inferência","sections":[{"title":"XLM","local":"xlm","sections":[{"title":"XLM com language embeddings","local":"xlm-com-language-embeddings","sections":[],"depth":3},{"title":"XLM sem language embeddings","local":"xlm-sem-language-embeddings","sections":[],"depth":3}],"depth":2},{"title":"BERT","local":"bert","sections":[],"depth":2},{"title":"XLM-RoBERTa","local":"xlm-roberta","sections":[],"depth":2},{"title":"M2M100","local":"m2m100","sections":[],"depth":2},{"title":"MBart","local":"mbart","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="modelos-multilinguísticos-para-inferência" 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-multilinguísticos-para-inferência"><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 data-svelte-h="svelte-16vg6ah">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/google-bert/bert-base-multilingual-uncased" rel="nofollow">google-bert/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 data-svelte-h="svelte-1b8wedt">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 data-svelte-h="svelte-1g05fmh">Os seguintes modelos de XLM usam language embeddings para especificar a linguagem utilizada para a inferência.</p> <ul data-svelte-h="svelte-bq7gp5"><li><code>FacebookAI/xlm-mlm-ende-1024</code> (Masked language modeling, English-German)</li> <li><code>FacebookAI/xlm-mlm-enfr-1024</code> (Masked language modeling, English-French)</li> <li><code>FacebookAI/xlm-mlm-enro-1024</code> (Masked language modeling, English-Romanian)</li> <li><code>FacebookAI/xlm-mlm-xnli15-1024</code> (Masked language modeling, XNLI languages)</li> <li><code>FacebookAI/xlm-mlm-tlm-xnli15-1024</code> (Masked language modeling + translation, XNLI languages)</li> <li><code>FacebookAI/xlm-clm-enfr-1024</code> (Causal language modeling, English-French)</li> <li><code>FacebookAI/xlm-clm-ende-1024</code> (Causal language modeling, English-German)</li></ul> <p data-svelte-h="svelte-1wzx267">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 data-svelte-h="svelte-16xglvw">Neste exemplo, carregamos o checkpoint <code>FacebookAI/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 class=""><!-- 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">"FacebookAI/xlm-clm-enfr-1024"</span>) | |
| <span class="hljs-meta">>>> </span>model = XLMWithLMHeadModel.from_pretrained(<span class="hljs-string">"FacebookAI/xlm-clm-enfr-1024"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1jlw8vy">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 class=""><!-- 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 data-svelte-h="svelte-fdserj">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 class=""><!-- 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 data-svelte-h="svelte-gr6p76">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 class=""><!-- 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 data-svelte-h="svelte-syxnxn">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 class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>outputs = model(input_ids, langs=langs)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1olpich">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 data-svelte-h="svelte-uu1fkj">Os seguintes modelos XLM não requerem o uso de language embeddings durante a inferência:</p> <ul data-svelte-h="svelte-1fta402"><li><code>FacebookAI/xlm-mlm-17-1280</code> (Modelagem de linguagem com máscara, 17 idiomas)</li> <li><code>FacebookAI/xlm-mlm-100-1280</code> (Modelagem de linguagem com máscara, 100 idiomas)</li></ul> <p data-svelte-h="svelte-1647i4h">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 data-svelte-h="svelte-1otw1i1">Os seguintes modelos do BERT podem ser utilizados para tarefas multilinguísticas:</p> <ul data-svelte-h="svelte-e6dubl"><li><code>google-bert/bert-base-multilingual-uncased</code> (Modelagem de linguagem com máscara + Previsão de frases, 102 idiomas)</li> <li><code>google-bert/bert-base-multilingual-cased</code> (Modelagem de linguagem com máscara + Previsão de frases, 104 idiomas)</li></ul> <p data-svelte-h="svelte-188d9hb">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="xlm-roberta" 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-roberta"><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 data-svelte-h="svelte-1on8run">Os seguintes modelos do XLM-RoBERTa podem ser utilizados para tarefas multilinguísticas:</p> <ul data-svelte-h="svelte-10y283s"><li><code>FacebookAI/xlm-roberta-base</code> (Modelagem de linguagem com máscara, 100 idiomas)</li> <li><code>FacebookAI/xlm-roberta-large</code> Modelagem de linguagem com máscara, 100 idiomas)</li></ul> <p data-svelte-h="svelte-1mo7moz">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 data-svelte-h="svelte-1uzzyuv">Os seguintes modelos de M2M100 podem ser utilizados para traduções multilinguísticas:</p> <ul data-svelte-h="svelte-1811mz9"><li><code>facebook/m2m100_418M</code> (Tradução)</li> <li><code>facebook/m2m100_1.2B</code> (Tradução)</li></ul> <p data-svelte-h="svelte-18dxqmr">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 class=""><!-- 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 data-svelte-h="svelte-6ksz4d">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 class=""><!-- 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 data-svelte-h="svelte-1k8y33q">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 class=""><!-- 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 data-svelte-h="svelte-i72hny">Os seguintes modelos do MBart podem ser utilizados para tradução multilinguística:</p> <ul data-svelte-h="svelte-1wsg399"><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 data-svelte-h="svelte-134fnsi">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 class=""><!-- 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 data-svelte-h="svelte-u1agxv">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 class=""><!-- 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 data-svelte-h="svelte-ybbnzp">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 class=""><!-- 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 data-svelte-h="svelte-quxms0">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> <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/multilingual.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, 9], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 39.8 kB
- Xet hash:
- 9e9e3a3ba965dbd27954c5b4698249fb888b95de25db655f5c0d728c801d1e47
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.