Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"O que fazer quando ocorrer um erro","local":"o-que-fazer-quando-ocorrer-um-erro","sections":[{"title":"Debugando o pipeline de 🤗 Transformers","local":"debugando-o-pipeline-de--transformers","sections":[],"depth":2},{"title":"Debugando o forward pass do seu modelo","local":"debugando-o-forward-pass-do-seu-modelo","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/course/pr_1069/pt/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/entry/start.854f6ddb.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/scheduler.37c15a92.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/singletons.5a4db441.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/index.18351ede.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/paths.052a2e73.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/entry/app.99d5705b.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/index.2bf4358c.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/nodes/0.24f28b67.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/nodes/41.b177bdb8.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/Tip.363c041f.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/Youtube.1e50a667.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/CodeBlock.4e987730.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/CourseFloatingBanner.6add7356.js"> | |
| <link rel="modulepreload" href="/docs/course/pr_1069/pt/_app/immutable/chunks/getInferenceSnippets.24b50994.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"O que fazer quando ocorrer um erro","local":"o-que-fazer-quando-ocorrer-um-erro","sections":[{"title":"Debugando o pipeline de 🤗 Transformers","local":"debugando-o-pipeline-de--transformers","sections":[],"depth":2},{"title":"Debugando o forward pass do seu modelo","local":"debugando-o-forward-pass-do-seu-modelo","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="o-que-fazer-quando-ocorrer-um-erro" 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="#o-que-fazer-quando-ocorrer-um-erro"><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>O que fazer quando ocorrer um erro</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-8-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/pt/chapter8/section2.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/pt/chapter8/section2.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-ex0u9e">Nesta seção, veremos alguns erros comuns que podem ocorrer ao tentar gerar previsões de seu modelo Transformer recém treinado. Isso irá prepará-lo para a <a href="/course/chapter8/section4">seção 4</a>, onde exploraremos como debugar a própria fase de treinamento.</p> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/DQ-CpJn6Rc4" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-16hicbb">Preparamos um <a href="https://huggingface.co/lewtun/distilbert-base-uncased-finetuned-squad-d5716d28" rel="nofollow">repositório modelo</a> para esta seção e, se você quiser executar o código neste capítulo, Primeiro, você precisará copiar o modelo para sua conta no <a href="https://huggingface.co" rel="nofollow">Hugging Face Hub</a>. Para fazer isso, primeiro faça login executando o seguinte em um notebook Jupyter:</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> huggingface_hub <span class="hljs-keyword">import</span> notebook_login | |
| notebook_login()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-v02co9">ou usando seu terminal favorito:</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 -->huggingface-cli login<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-bt02s1">Isso solicitará que você insira seu nome de usuário e senha e salvará um token em <em>~/.cache/huggingface/</em>. Depois de fazer login, você pode copiar o repositório de modelos com a seguinte função:</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> distutils.dir_util <span class="hljs-keyword">import</span> copy_tree | |
| <span class="hljs-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> Repository, snapshot_download, create_repo, get_full_repo_name | |
| <span class="hljs-keyword">def</span> <span class="hljs-title function_">copy_repository_template</span>(): | |
| <span class="hljs-comment"># Clone the repo and extract the local path</span> | |
| template_repo_id = <span class="hljs-string">"lewtun/distilbert-base-uncased-finetuned-squad-d5716d28"</span> | |
| commit_hash = <span class="hljs-string">"be3eaffc28669d7932492681cd5f3e8905e358b4"</span> | |
| template_repo_dir = snapshot_download(template_repo_id, revision=commit_hash) | |
| <span class="hljs-comment"># Create an empty repo on the Hub</span> | |
| model_name = template_repo_id.split(<span class="hljs-string">"/"</span>)[<span class="hljs-number">1</span>] | |
| create_repo(model_name, exist_ok=<span class="hljs-literal">True</span>) | |
| <span class="hljs-comment"># Clone the empty repo</span> | |
| new_repo_id = get_full_repo_name(model_name) | |
| new_repo_dir = model_name | |
| repo = Repository(local_dir=new_repo_dir, clone_from=new_repo_id) | |
| <span class="hljs-comment"># Copy files</span> | |
| copy_tree(template_repo_dir, new_repo_dir) | |
| <span class="hljs-comment"># Push to Hub</span> | |
| repo.push_to_hub()<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1gz8i9c">Agora, quando você chamar <code>copy_repository_template()</code>, ele criará uma cópia do repositório de modelos em sua conta.</p> <h2 class="relative group"><a id="debugando-o-pipeline-de--transformers" 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="#debugando-o-pipeline-de--transformers"><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>Debugando o pipeline de 🤗 Transformers</span></h2> <p data-svelte-h="svelte-1wn6qyy">Para iniciar nossa jornada no maravilhoso mundo de debug de modelos Transformer, considere o seguinte cenário: você está trabalhando com um colega em um projeto de resposta a perguntas para ajudar os clientes de um site de comércio eletrônico a encontrar respostas sobre produtos de consumo. Seu colega lhe envia uma mensagem como:</p> <blockquote data-svelte-h="svelte-dzk7h2"><p>Bom dia! Acabei de fazer um experimento usando as técnicas do <a href="/course/chapter7/7">Capítulo 7</a> do curso Hugging Face e obtive ótimos resultados no SQuAD! Acho que podemos usar esse modelo como checkpoint para o nosso projeto. O ID do modelo no Hub é “lewtun/distillbert-base-uncased-finetuned-squad-d5716d28”. Fique a vontade para testar :)</p></blockquote> <p data-svelte-h="svelte-qx4ax3">e a primeira coisa que você pensa é carregar o modelo usando o <code>pipeline</code> de 🤗 Transformers:</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> transformers <span class="hljs-keyword">import</span> pipeline | |
| model_checkpoint = get_full_repo_name(<span class="hljs-string">"distillbert-base-uncased-finetuned-squad-d5716d28"</span>) | |
| reader = pipeline(<span class="hljs-string">"question-answering"</span>, model=model_checkpoint)<!-- HTML_TAG_END --></pre></div> <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-string">""" | |
| OSError: Can't load config for 'lewtun/distillbert-base-uncased-finetuned-squad-d5716d28'. Make sure that: | |
| - 'lewtun/distillbert-base-uncased-finetuned-squad-d5716d28' is a correct model identifier listed on 'https://huggingface.co/models' | |
| - or 'lewtun/distillbert-base-uncased-finetuned-squad-d5716d28' is the correct path to a directory containing a config.json file | |
| """</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-o4ggc2">Oh não, algo parece ter dado errado! Se você é novo em programação, esse tipo de erro pode parecer um pouco enigmático no começo (o que é mesmo um <code>OSError</code>?!). O erro exibido aqui é apenas a última parte de um relatório de erros muito maior chamado <em>Python traceback</em> (também conhecido como <strong>stack trace</strong>). Por exemplo, se você estiver executando este código no Google Colab, deverá ver algo como a captura de tela a seguir:</p> <div class="flex justify-center" data-svelte-h="svelte-1196hzp"><img src="https://huggingface.co/datasets/huggingface-course/documentation-images/resolve/main/en/chapter8/traceback.png" alt="A Python traceback." width="100%"></div> <p data-svelte-h="svelte-pgirhp">Há muitas informações contidas nesses relatórios, então vamos percorrer as partes principais juntos. A primeira coisa a notar é que os tracebacks devem ser lidos <em>de baixo para cima</em>. Isso pode soar estranho se você está acostumado a ler texto em inglês de cima para baixo, mas reflete o fato de que o traceback mostra a sequência de chamadas de função que o <code>pipeline</code> faz ao baixar o modelo e o tokenizer. (Confira o <a href="/course/chapter2">Capítulo 2</a> para mais detalhes sobre como o <code>pipeline</code> funciona nos bastidores.)</p> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-12l7ict">🚨 Está vendo aquela caixa azul em torno de “6 frames” no traceback do Google Colab? Esse é um recurso especial do Colab, que compacta o traceback em “quadros”. Se você não conseguir encontrar a fonte de um erro, certifique-se de expandir o rastreamento completo clicando nessas duas pequenas setas.</p></div> <p data-svelte-h="svelte-fv27iy">Isso significa que a última linha do traceback indica a última mensagem de erro e fornece o nome da exceção que foi gerada. Nesse caso, o tipo de exceção é <code>OSError</code>, que indica um erro relacionado ao sistema. Se lermos a mensagem de erro que a acompanha, veremos que parece haver um problema com o arquivo <em>config.json</em> do modelo e recebemos duas sugestões para corrigi-lo:</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-string">""" | |
| Make sure that: | |
| - 'lewtun/distillbert-base-uncased-finetuned-squad-d5716d28' is a correct model identifier listed on 'https://huggingface.co/models' | |
| - or 'lewtun/distillbert-base-uncased-finetuned-squad-d5716d28' is the correct path to a directory containing a config.json file | |
| """</span><!-- HTML_TAG_END --></pre></div> <div class="course-tip bg-gradient-to-br dark:bg-gradient-to-r before:border-green-500 dark:before:border-green-800 from-green-50 dark:from-gray-900 to-white dark:to-gray-950 border border-green-50 text-green-700 dark:text-gray-400"><p data-svelte-h="svelte-8n8jo3">💡 Se você encontrar uma mensagem de erro difícil de entender, basta copiar e colar a mensagem na barra de pesquisa do Google ou <a href="https://stackoverflow.com/" rel="nofollow">Stack Overflow</a> (sim, sério!). Há uma boa chance de você não ser a primeira pessoa a encontrar o erro, e essa é uma boa maneira de encontrar soluções que outras pessoas da comunidade postaram. Por exemplo, pesquisar por <code>OSError: Can't load config for</code> no Stack Overflow fornece vários <a href="https://stackoverflow.com/search?q=OSError%3A+Can%27t+load+config+for+" rel="nofollow">hits</a> que poderia ser usado como ponto de partida para resolver o problema.</p></div> <p data-svelte-h="svelte-wy4r6f">A primeira sugestão é nos pedir para verificar se o ID do modelo está realmente correto, então a primeira ordem do dia é copiar o identificador e colá-lo na barra de pesquisa do Hub:</p> <div class="flex justify-center" data-svelte-h="svelte-6ebc1j"><img src="https://huggingface.co/datasets/huggingface-course/documentation-images/resolve/main/en/chapter8/wrong-model-id.png" alt="The wrong model name." width="100%"></div> <p data-svelte-h="svelte-zcshde">Hmm, realmente parece que o modelo do nosso colega não está no Hub… aha, mas há um erro de digitação no nome do modelo! DistilBERT tem apenas um “l” em seu nome, então vamos corrigir isso e procurar por “lewtun/distilbert-base-uncased-finetuned-squad-d5716d28”:</p> <div class="flex justify-center" data-svelte-h="svelte-1b95mxr"><img src="https://huggingface.co/datasets/huggingface-course/documentation-images/resolve/main/en/chapter8/true-model-id.png" alt="The right model name." width="100%"></div> <p data-svelte-h="svelte-1aaic6w">Ok, isso teve sucesso. Agora vamos tentar baixar o modelo novamente com o ID do modelo correto:</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 -->model_checkpoint = get_full_repo_name(<span class="hljs-string">"distilbert-base-uncased-finetuned-squad-d5716d28"</span>) | |
| reader = pipeline(<span class="hljs-string">"question-answering"</span>, model=model_checkpoint)<!-- HTML_TAG_END --></pre></div> <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-string">""" | |
| OSError: Can't load config for 'lewtun/distilbert-base-uncased-finetuned-squad-d5716d28'. Make sure that: | |
| - 'lewtun/distilbert-base-uncased-finetuned-squad-d5716d28' is a correct model identifier listed on 'https://huggingface.co/models' | |
| - or 'lewtun/distilbert-base-uncased-finetuned-squad-d5716d28' is the correct path to a directory containing a config.json file | |
| """</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1djb1gb">Argh, frustrado novamente - bem-vindo ao cotidiano de um engenheiro de aprendizado de máquina! Como corrigimos o ID do modelo, o problema deve estar no próprio repositório. Uma maneira rápida de acessar o conteúdo de um repositório no 🤗 Hub é através da função <code>list_repo_files()</code> da biblioteca <code>huggingface_hub</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-keyword">from</span> huggingface_hub <span class="hljs-keyword">import</span> list_repo_files | |
| list_repo_files(repo_id=model_checkpoint)<!-- HTML_TAG_END --></pre></div> <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-string">'.gitattributes'</span>, <span class="hljs-string">'README.md'</span>, <span class="hljs-string">'pytorch_model.bin'</span>, <span class="hljs-string">'special_tokens_map.json'</span>, <span class="hljs-string">'tokenizer_config.json'</span>, <span class="hljs-string">'training_args.bin'</span>, <span class="hljs-string">'vocab.txt'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-85ft17">Interessante — não parece haver um arquivo <em>config.json</em> no repositório! Não é à toa que nosso <code>pipeline</code> não conseguiu carregar o modelo; nosso colega deve ter esquecido de enviar este arquivo para o Hub depois de ajustá-lo. Nesse caso, o problema parece bem simples de corrigir: poderíamos pedir para adicionar o arquivo ou, como podemos ver no ID do modelo, que o modelo pré-treinado usado foi [<code>distilbert-base-uncased</code>](https:/ /huggingface.co/distilbert-base-uncased), podemos baixar a configuração para este modelo e enviá-la para nosso repositório para ver se isso resolve o problema. Vamos tentar isso. Usando as técnicas que aprendemos no <a href="/course/chapter2">Capítulo 2</a>, podemos baixar a configuração do modelo com a classe <code>AutoConfig</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-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoConfig | |
| pretrained_checkpoint = <span class="hljs-string">"distilbert-base-uncased"</span> | |
| config = AutoConfig.from_pretrained(pretrained_checkpoint)<!-- HTML_TAG_END --></pre></div> <div class="course-tip course-tip-orange bg-gradient-to-br dark:bg-gradient-to-r before:border-orange-500 dark:before:border-orange-800 from-orange-50 dark:from-gray-900 to-white dark:to-gray-950 border border-orange-50 text-orange-700 dark:text-gray-400"><p data-svelte-h="svelte-8akbf3">🚨 A abordagem que estamos tomando aqui não é infalível, já que nosso colega pode ter ajustado a configuração de <code>distilbert-base-uncased</code> antes de ajustar o modelo. Na vida real, gostaríamos de verificar com eles primeiro, mas para os propósitos desta seção, vamos supor que eles usaram a configuração padrão.</p></div> <p data-svelte-h="svelte-1289nqx">Podemos então enviar isso para o nosso repositório de modelos com a função <code>push_to_hub()</code> da configuração:</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 -->config.push_to_hub(model_checkpoint, commit_message=<span class="hljs-string">"Add config.json"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1wyrpnj">Agora podemos testar se funcionou carregando o modelo do último commit no branch <code>main</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 -->reader = pipeline(<span class="hljs-string">"question-answering"</span>, model=model_checkpoint, revision=<span class="hljs-string">"main"</span>) | |
| context = <span class="hljs-string">r""" | |
| Extractive Question Answering is the task of extracting an answer from a text | |
| given a question. An example of a question answering dataset is the SQuAD | |
| dataset, which is entirely based on that task. If you would like to fine-tune a | |
| model on a SQuAD task, you may leverage the | |
| examples/pytorch/question-answering/run_squad.py script. | |
| 🤗 Transformers is interoperable with the PyTorch, TensorFlow, and JAX | |
| frameworks, so you can use your favourite tools for a wide variety of tasks! | |
| """</span> | |
| question = <span class="hljs-string">"What is extractive question answering?"</span> | |
| reader(question=question, context=context)<!-- HTML_TAG_END --></pre></div> <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-string">'score'</span>: <span class="hljs-number">0.38669535517692566</span>, | |
| <span class="hljs-string">'start'</span>: <span class="hljs-number">34</span>, | |
| <span class="hljs-string">'end'</span>: <span class="hljs-number">95</span>, | |
| <span class="hljs-string">'answer'</span>: <span class="hljs-string">'the task of extracting an answer from a text given a question'</span>}<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-3umfqs">Uhuuul, funcionou! Vamos recapitular o que você acabou de aprender:</p> <ul data-svelte-h="svelte-m10ea2"><li>As mensagens de erro em Python são conhecidas como <em>tracebacks</em> e são lidas de baixo para cima. A última linha da mensagem de erro geralmente contém as informações necessárias para localizar a origem do problema.</li> <li>Se a última linha não contiver informações suficientes, suba o traceback e veja se você consegue identificar onde no código-fonte o erro ocorre.</li> <li>Se nenhuma das mensagens de erro puder ajudá-lo a debugar o problema, tente pesquisar online uma solução para um problema semelhante.</li> <li>O <code>huggingface_hub</code> | |
| // 🤗 Hub? | |
| esta biblioteca fornece um conjunto de ferramentas que você pode usar para interagir e debugar repositórios no Hub.</li></ul> <p data-svelte-h="svelte-18439xh">Agora que você sabe como debugar um pipeline, vamos dar uma olhada em um exemplo mais complicado no forward pass do próprio modelo.</p> <h2 class="relative group"><a id="debugando-o-forward-pass-do-seu-modelo" 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="#debugando-o-forward-pass-do-seu-modelo"><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>Debugando o forward pass do seu modelo</span></h2> <p data-svelte-h="svelte-1g83fu3">Embora o <code>pipeline</code> seja ótimo para a maioria dos aplicativos em que você precisa gerar previsões rapidamente, às vezes você precisará acessar os logits do modelo (digamos, se você tiver algum pós-processamento personalizado que gostaria de aplicar). Para ver o que pode dar errado neste caso, vamos primeiro pegar o modelo e o tokenizer do nosso <code>pipeline</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 -->tokenizer = reader.tokenizer | |
| model = reader.model<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1uwz12k">Em seguida, precisamos de uma pergunta, então vamos ver se nossos frameworks favoritos são suportados:</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 -->question = <span class="hljs-string">"Which frameworks can I use?"</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-i9ytg0">Como vimos no <a href="/course/chapter7">Capítulo 7</a>, as etapas usuais que precisamos seguir são tokenizar as entradas, extrair os logits dos tokens de início e fim e, em seguida, decodificar o intervalo de resposta:</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">import</span> torch | |
| inputs = tokenizer(question, context, add_special_tokens=<span class="hljs-literal">True</span>) | |
| input_ids = inputs[<span class="hljs-string">"input_ids"</span>][<span class="hljs-number">0</span>] | |
| outputs = model(**inputs) | |
| answer_start_scores = outputs.start_logits | |
| answer_end_scores = outputs.end_logits | |
| <span class="hljs-comment"># Get the most likely beginning of answer with the argmax of the score</span> | |
| answer_start = torch.argmax(answer_start_scores) | |
| <span class="hljs-comment"># Get the most likely end of answer with the argmax of the score</span> | |
| answer_end = torch.argmax(answer_end_scores) + <span class="hljs-number">1</span> | |
| answer = tokenizer.convert_tokens_to_string( | |
| tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]) | |
| ) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Question: <span class="hljs-subst">{question}</span>"</span>) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Answer: <span class="hljs-subst">{answer}</span>"</span>)<!-- HTML_TAG_END --></pre></div> <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-string">""" | |
| --------------------------------------------------------------------------- | |
| AttributeError Traceback (most recent call last) | |
| /var/folders/28/k4cy5q7s2hs92xq7_h89_vgm0000gn/T/ipykernel_75743/2725838073.py in <module> | |
| 1 inputs = tokenizer(question, text, add_special_tokens=True) | |
| 2 input_ids = inputs["input_ids"] | |
| ----> 3 outputs = model(**inputs) | |
| 4 answer_start_scores = outputs.start_logits | |
| 5 answer_end_scores = outputs.end_logits | |
| ~/miniconda3/envs/huggingface/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) | |
| 1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks | |
| 1050 or _global_forward_hooks or _global_forward_pre_hooks): | |
| -> 1051 return forward_call(*input, **kwargs) | |
| 1052 # Do not call functions when jit is used | |
| 1053 full_backward_hooks, non_full_backward_hooks = [], [] | |
| ~/miniconda3/envs/huggingface/lib/python3.8/site-packages/transformers/models/distilbert/modeling_distilbert.py in forward(self, input_ids, attention_mask, head_mask, inputs_embeds, start_positions, end_positions, output_attentions, output_hidden_states, return_dict) | |
| 723 return_dict = return_dict if return_dict is not None else self.config.use_return_dict | |
| 724 | |
| --> 725 distilbert_output = self.distilbert( | |
| 726 input_ids=input_ids, | |
| 727 attention_mask=attention_mask, | |
| ~/miniconda3/envs/huggingface/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs) | |
| 1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks | |
| 1050 or _global_forward_hooks or _global_forward_pre_hooks): | |
| -> 1051 return forward_call(*input, **kwargs) | |
| 1052 # Do not call functions when jit is used | |
| 1053 full_backward_hooks, non_full_backward_hooks = [], [] | |
| ~/miniconda3/envs/huggingface/lib/python3.8/site-packages/transformers/models/distilbert/modeling_distilbert.py in forward(self, input_ids, attention_mask, head_mask, inputs_embeds, output_attentions, output_hidden_states, return_dict) | |
| 471 raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time") | |
| 472 elif input_ids is not None: | |
| --> 473 input_shape = input_ids.size() | |
| 474 elif inputs_embeds is not None: | |
| 475 input_shape = inputs_embeds.size()[:-1] | |
| AttributeError: 'list' object has no attribute 'size' | |
| """</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1ytx60u">Oxii, parece que temos um bug em nosso código! Mas não temos medo de debugar um pouco. Você pode usar o debugger do Python em um notebook:</p> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/rSPyvPw0p9k" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-1dit4ui">ou em um terminal:</p> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/5PkZ4rbHL6c" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-1r100qj">Aqui, a leitura da mensagem de erro nos diz que o objeto <code>'list' não tem atributo 'size'</code>, e podemos ver uma seta <code>--></code> apontando para a linha onde o problema foi levantado em <code>model(**inputs) </code>. Você pode debugar isso interativamente usando o debugger Python, mas por enquanto vamos simplesmente imprimir uma fatia de <code>entradas</code> para ver o que temos:</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 -->inputs[<span class="hljs-string">"input_ids"</span>][:<span class="hljs-number">5</span>]<!-- HTML_TAG_END --></pre></div> <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-number">101</span>, <span class="hljs-number">2029</span>, <span class="hljs-number">7705</span>, <span class="hljs-number">2015</span>, <span class="hljs-number">2064</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-5fyj9g">Isso certamente se parece com uma <code>lista</code> comum do Python, mas vamos verificar novamente o tipo:</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-built_in">type</span>(inputs[<span class="hljs-string">"input_ids"</span>])<!-- HTML_TAG_END --></pre></div> <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">list</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-t2hq6r">Sim, isso é uma <code>lista</code> do Python com certeza. Então o que deu errado? Lembre-se do <a href="/course/chapter2">Capítulo 2</a> que as classes <code>AutoModelForXxx</code> em 🤗 Transformers operam em <em>tensors</em> (em PyTorch ou TensorFlow), e uma operação comum é extrair as dimensões de um tensor usando <code>Tensor.size( )</code> em, digamos, PyTorch. Vamos dar outra olhada no traceback, para ver qual linha acionou a exceção:</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-regexp">/miniconda3/</span>envs<span class="hljs-regexp">/huggingface/</span>lib<span class="hljs-regexp">/python3.8/</span>site-packages<span class="hljs-regexp">/transformers/m</span>odels<span class="hljs-regexp">/distilbert/m</span>odeling_distilbert.py in forward(self, input_ids, attention_mask, head_mask, inputs_embeds, output_attentions, output_hidden_states, return_dict) | |
| <span class="hljs-number">471</span> raise ValueError(<span class="hljs-string">"You cannot specify both input_ids and inputs_embeds at the same time"</span>) | |
| <span class="hljs-number">472</span> elif input_ids is not None: | |
| --> <span class="hljs-number">473</span> input_shape = input_ids.<span class="hljs-keyword">size</span>() | |
| <span class="hljs-number">474</span> elif inputs_embeds is not None: | |
| <span class="hljs-number">475</span> input_shape = inputs_embeds.<span class="hljs-keyword">size</span>()[:-<span class="hljs-number">1</span>] | |
| AttributeError: <span class="hljs-string">'list'</span> object has no attribute <span class="hljs-string">'size'</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-13i7ql">Parece que nosso código tentou chamar <code>input_ids.size()</code>, mas isso claramente não funcionará para uma <code>list</code> Python, que é apenas um contêiner. Como podemos resolver este problema? Pesquisar a mensagem de erro no Stack Overflow fornece alguns [hits] relevantes (<a href="https://stackoverflow.com/search?q=AttributeError%3A+%27list%27+object+has+no+attribute+%27size%27&s=c15ec54c-63cb-481d-a749-408920073e8f" rel="nofollow">https://stackoverflow.com/search?q=AttributeError%3A+%27list%27+object+has+no+attribute+%27size%27&s=c15ec54c-63cb-481d-a749-408920073e8f</a>). Clicar no primeiro exibe uma pergunta semelhante à nossa, com a resposta mostrada na captura de tela abaixo:</p> <div class="flex justify-center" data-svelte-h="svelte-1i8wi5i"><img src="https://huggingface.co/datasets/huggingface-course/documentation-images/resolve/main/en/chapter8/stack-overflow.png" alt="An answer from Stack Overflow." width="100%"></div> <p data-svelte-h="svelte-ku4msr">A resposta recomenda que adicionemos <code>return_tensors='pt'</code> ao tokenizer, então vamos ver se isso funciona para nós:</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 -->inputs = tokenizer(question, context, add_special_tokens=<span class="hljs-literal">True</span>, return_tensors=<span class="hljs-string">"pt"</span>) | |
| input_ids = inputs[<span class="hljs-string">"input_ids"</span>][<span class="hljs-number">0</span>] | |
| outputs = model(**inputs) | |
| answer_start_scores = outputs.start_logits | |
| answer_end_scores = outputs.end_logits | |
| <span class="hljs-comment"># Get the most likely beginning of answer with the argmax of the score</span> | |
| answer_start = torch.argmax(answer_start_scores) | |
| <span class="hljs-comment"># Get the most likely end of answer with the argmax of the score</span> | |
| answer_end = torch.argmax(answer_end_scores) + <span class="hljs-number">1</span> | |
| answer = tokenizer.convert_tokens_to_string( | |
| tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]) | |
| ) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Question: <span class="hljs-subst">{question}</span>"</span>) | |
| <span class="hljs-built_in">print</span>(<span class="hljs-string">f"Answer: <span class="hljs-subst">{answer}</span>"</span>)<!-- HTML_TAG_END --></pre></div> <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-string">""" | |
| Question: Which frameworks can I use? | |
| Answer: pytorch, tensorflow, and jax | |
| """</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-o2so2i">Legal, funcionou! Este é um ótimo exemplo de como o Stack Overflow pode ser útil: ao identificar um problema semelhante, pudemos nos beneficiar da experiência de outras pessoas da comunidade. No entanto, uma pesquisa como essa nem sempre produz uma resposta relevante, então o que você pode fazer nesses casos? Felizmente, há uma comunidade acolhedora de desenvolvedores nos <a href="https://discuss.huggingface.co/" rel="nofollow">fóruns do Hugging Face</a> que pode ajudá-lo! Na próxima seção, veremos como você pode criar boas perguntas no fórum que provavelmente serão respondidas.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/pt/chapter8/2.mdx" 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_1ef170a = { | |
| assets: "/docs/course/pr_1069/pt", | |
| base: "/docs/course/pr_1069/pt", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/course/pr_1069/pt/_app/immutable/entry/start.854f6ddb.js"), | |
| import("/docs/course/pr_1069/pt/_app/immutable/entry/app.99d5705b.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 41], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 67.7 kB
- Xet hash:
- e2aa61cf3ac96a0e588db413b25c91d6a79d65ec2a1aa06646f1db1cf73cc433
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.