Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / course /pr_1306 /it /chapter3 /6.html

HuggingFaceDocBuilder

28 days ago

download

raw

36.8 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Quiz di fine capitolo","local":"quiz-di-fine-capitolo","sections":[{"title":"1. Il dataset emotion contiene messaggi Twitter etichettati con emozioni. Cercalo nel Hub e leggi la carta del dataset. Quale di queste non fa parte delle sue emozioni di base?","local":"1-il-dataset-emotion-contiene-messaggi-twitter-etichettati-con-emozioni-cercalo-nel-hub-e-leggi-la-carta-del-dataset-quale-di-queste-non-fa-parte-delle-sue-emozioni-di-base","sections":[],"depth":3},{"title":"2. Cerca il dataset ar_sarcasm nel Hub . Quali compiti supporta?","local":"2-cerca-il-dataset-arsarcasm-nel-hub--quali-compiti-supporta","sections":[],"depth":3},{"title":"3. Come deve essere preparata una coppia di frasi per essere processata dal modello BERT?","local":"3-come-deve-essere-preparata-una-coppia-di-frasi-per-essere-processata-dal-modello-bert","sections":[],"depth":3},{"title":"4. Quali sono i benefici del metodo Dataset.map() ?","local":"4-quali-sono-i-benefici-del-metodo-datasetmap-","sections":[],"depth":3},{"title":"5. Qual è il significato di padding dinamico (dynamic padding)?","local":"5-qual-è-il-significato-di-padding-dinamico-dynamic-padding","sections":[],"depth":3},{"title":"6. Qual è lo scopo di una funzione di raccolta (collate function)?","local":"6-qual-è-lo-scopo-di-una-funzione-di-raccolta-collate-function","sections":[],"depth":3},{"title":"7. Cosa succede quando una classe di tipo AutoModelForXxx viene istanziata con un modello di linguaggio pre-addestrato (come bert-base-uncased ) che corrisponde ad un compito differente rispetto a quello per cui era stato addestrato?","local":"7-cosa-succede-quando-una-classe-di-tipo-automodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato","sections":[],"depth":3},{"title":"8. Qual è lo scopo di TrainingArguments ?","local":"8-qual-è-lo-scopo-di-trainingarguments-","sections":[],"depth":3},{"title":"9. Perché si dovrebbe usare la libreria 🤗 Accelerate?","local":"9-perché-si-dovrebbe-usare-la-libreria--accelerate","sections":[],"depth":3},{"title":"4. Cosa succede quando una classe di tipo TFAutoModelForXxx viene istanziata con un modello di linguaggio pre-addestrato (come bert-base-uncased ) che corrisponde ad un compito differente rispetto a quello per cui era stato addestrato?","local":"4-cosa-succede-quando-una-classe-di-tipo-tfautomodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato","sections":[],"depth":3},{"title":"5. I modelli Tensorflow da transformers sono già dei modelli Keras. Quali benefici offre ciò?","local":"5-i-modelli-tensorflow-da-transformers-sono-già-dei-modelli-keras-quali-benefici-offre-ciò","sections":[],"depth":3},{"title":"6. Come si definisce una metrica personalizzata (custom metric)?","local":"6-come-si-definisce-una-metrica-personalizzata-custom-metric","sections":[],"depth":3}],"depth":1}"/>
	<link href="/docs/course/pr_1306/it/_app/immutable/entry/start.CT6zZwAy.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/BTGjBc5n.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/C1g_JXwL.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/entry/app.DTrNdXKl.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/CI14Xrrj.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/CtQcHPv9.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/vP7Qbn5Z.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/nodes/0.Dv6OVTT8.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/ChX01CHW.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/nodes/26.PNSEktRa.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/DlGKhtLA.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/zvU8pyBI.js" rel="modulepreload">
	<link href="/docs/course/pr_1306/it/_app/immutable/chunks/DJehu_xf.js" rel="modulepreload">
	<!--45qh00--><meta name="hf:doc:metadata" content="{"title":"Quiz di fine capitolo","local":"quiz-di-fine-capitolo","sections":[{"title":"1. Il dataset emotion contiene messaggi Twitter etichettati con emozioni. Cercalo nel Hub e leggi la carta del dataset. Quale di queste non fa parte delle sue emozioni di base?","local":"1-il-dataset-emotion-contiene-messaggi-twitter-etichettati-con-emozioni-cercalo-nel-hub-e-leggi-la-carta-del-dataset-quale-di-queste-non-fa-parte-delle-sue-emozioni-di-base","sections":[],"depth":3},{"title":"2. Cerca il dataset ar_sarcasm nel Hub . Quali compiti supporta?","local":"2-cerca-il-dataset-arsarcasm-nel-hub--quali-compiti-supporta","sections":[],"depth":3},{"title":"3. Come deve essere preparata una coppia di frasi per essere processata dal modello BERT?","local":"3-come-deve-essere-preparata-una-coppia-di-frasi-per-essere-processata-dal-modello-bert","sections":[],"depth":3},{"title":"4. Quali sono i benefici del metodo Dataset.map() ?","local":"4-quali-sono-i-benefici-del-metodo-datasetmap-","sections":[],"depth":3},{"title":"5. Qual è il significato di padding dinamico (dynamic padding)?","local":"5-qual-è-il-significato-di-padding-dinamico-dynamic-padding","sections":[],"depth":3},{"title":"6. Qual è lo scopo di una funzione di raccolta (collate function)?","local":"6-qual-è-lo-scopo-di-una-funzione-di-raccolta-collate-function","sections":[],"depth":3},{"title":"7. Cosa succede quando una classe di tipo AutoModelForXxx viene istanziata con un modello di linguaggio pre-addestrato (come bert-base-uncased ) che corrisponde ad un compito differente rispetto a quello per cui era stato addestrato?","local":"7-cosa-succede-quando-una-classe-di-tipo-automodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato","sections":[],"depth":3},{"title":"8. Qual è lo scopo di TrainingArguments ?","local":"8-qual-è-lo-scopo-di-trainingarguments-","sections":[],"depth":3},{"title":"9. Perché si dovrebbe usare la libreria 🤗 Accelerate?","local":"9-perché-si-dovrebbe-usare-la-libreria--accelerate","sections":[],"depth":3},{"title":"4. Cosa succede quando una classe di tipo TFAutoModelForXxx viene istanziata con un modello di linguaggio pre-addestrato (come bert-base-uncased ) che corrisponde ad un compito differente rispetto a quello per cui era stato addestrato?","local":"4-cosa-succede-quando-una-classe-di-tipo-tfautomodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato","sections":[],"depth":3},{"title":"5. I modelli Tensorflow da transformers sono già dei modelli Keras. Quali benefici offre ciò?","local":"5-i-modelli-tensorflow-da-transformers-sono-già-dei-modelli-keras-quali-benefici-offre-ciò","sections":[],"depth":3},{"title":"6. Come si definisce una metrica personalizzata (custom metric)?","local":"6-come-si-definisce-una-metrica-personalizzata-custom-metric","sections":[],"depth":3}],"depth":1}"/><!---->
	<link href="/docs/course/pr_1306/it/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="bg-white leading-none border border-gray-100 rounded-lg flex p-0.5 w-56 text-sm mb-4"><!--[--><a class="flex justify-center flex-1 py-1.5 px-2.5 focus:outline-none !no-underline rounded-l bg-red-50 dark:bg-transparent text-red-600" href="?fw=pt"><!--[--><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><defs><clipPath id="a"><rect x="3.05" y="0.5" width="25.73" height="31" fill="none"></rect></clipPath></defs><g clip-path="url(#a)"><path d="M24.94,9.51a12.81,12.81,0,0,1,0,18.16,12.68,12.68,0,0,1-18,0,12.81,12.81,0,0,1,0-18.16l9-9V5l-.84.83-6,6a9.58,9.58,0,1,0,13.55,0ZM20.44,9a1.68,1.68,0,1,1,1.67-1.67A1.68,1.68,0,0,1,20.44,9Z" fill="#ee4c2c"></path></g></svg><!--]--> Pytorch</a><a class="flex justify-center flex-1 py-1.5 px-2.5 focus:outline-none !no-underline rounded-r text-gray-500 filter grayscale" href="?fw=tf"><!--[--><svg class="mr-1.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width="0.94em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 274"><path d="M145.726 42.065v42.07l72.861 42.07v-42.07l-72.86-42.07zM0 84.135v42.07l36.43 21.03V105.17L0 84.135zm109.291 21.035l-36.43 21.034v126.2l36.43 21.035v-84.135l36.435 21.035v-42.07l-36.435-21.034V105.17z" fill="#E55B2D"></path><path d="M145.726 42.065L36.43 105.17v42.065l72.861-42.065v42.065l36.435-21.03v-84.14zM255.022 63.1l-36.435 21.035v42.07l36.435-21.035V63.1zm-72.865 84.135l-36.43 21.035v42.07l36.43-21.036v-42.07zm-36.43 63.104l-36.436-21.035v84.135l36.435-21.035V210.34z" fill="#ED8E24"></path><path d="M145.726 0L0 84.135l36.43 21.035l109.296-63.105l72.861 42.07L255.022 63.1L145.726 0zm0 126.204l-36.435 21.03l36.435 21.036l36.43-21.035l-36.43-21.03z" fill="#F8BF3C"></path></svg><!--]--> TensorFlow</a><!--]--></div><!----> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="quiz-di-fine-capitolo" 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="#quiz-di-fine-capitolo"><span><svg 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>Quiz di fine capitolo</span></h1><!--]--><!----> <p>Testiamo cosa avete imparato in questo capitolo!</p> <!--[2--><h3 class="relative group"><a id="1-il-dataset-emotion-contiene-messaggi-twitter-etichettati-con-emozioni-cercalo-nel-hub-e-leggi-la-carta-del-dataset-quale-di-queste-non-fa-parte-delle-sue-emozioni-di-base" 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="#1-il-dataset-emotion-contiene-messaggi-twitter-etichettati-con-emozioni-cercalo-nel-hub-e-leggi-la-carta-del-dataset-quale-di-queste-non-fa-parte-delle-sue-emozioni-di-base"><span><svg 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>1. Il dataset emotion contiene messaggi Twitter etichettati con emozioni. Cercalo nel Hub e leggi la carta del dataset. Quale di queste non fa parte delle sue emozioni di base?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Joy (Gioia)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->Love (Amore)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Confusion (Confusione)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Surprise (Sorpresa)<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="2-cerca-il-dataset-arsarcasm-nel-hub--quali-compiti-supporta" 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="#2-cerca-il-dataset-arsarcasm-nel-hub--quali-compiti-supporta"><span><svg 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>2. Cerca il dataset ar_sarcasm nel Hub . Quali compiti supporta?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Sentiment classification (Classificazione dei sentimenti)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->Machine translation (Traduzione automatica)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Named entity recognition (Riconoscimento di entità con un nome)<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Question answering (Risposte a domande)<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="3-come-deve-essere-preparata-una-coppia-di-frasi-per-essere-processata-dal-modello-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="#3-come-deve-essere-preparata-una-coppia-di-frasi-per-essere-processata-dal-modello-bert"><span><svg 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>3. Come deve essere preparata una coppia di frasi per essere processata dal modello BERT?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Tokens_della_frase_1 [SEP] Tokens_della_frase_2<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->[CLS] Tokens_della_frase_1 Tokens_della_frase_2<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->[CLS] Tokens_della_frase_1 [SEP] Tokens_della_frase_2 [SEP]<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->[CLS] Tokens_della_frase_1 [SEP] Tokens_della_frase_2<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[0--><!--[2--><h3 class="relative group"><a id="4-quali-sono-i-benefici-del-metodo-datasetmap-" 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="#4-quali-sono-i-benefici-del-metodo-datasetmap-"><span><svg 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>4. Quali sono i benefici del metodo Dataset.map() ?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->I risultati della funzione vengono conservati, così la ri-esecuzione del codice sarà rapidissima<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->È possibile applicare multiprocessing per un'esecuzione più rapida rispetto all'applicazione seriale ad ogni elemento del dataset<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Non carica l'intero dataset in memoria, salvando i risultati appena ogni elemento è stato processato.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="5-qual-è-il-significato-di-padding-dinamico-dynamic-padding" 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="#5-qual-è-il-significato-di-padding-dinamico-dynamic-padding"><span><svg 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>5. Qual è il significato di padding dinamico (dynamic padding)?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->È quando si applica in ogni batch il padding fino alla lunghezza massima dell'intero dataset<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->È quando si applica in ogni batch il padding fino alla lunghezza massima delle frasi in quella batch<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->È quando si applica il padding agli input in modo che ogni frase abbia lo stesso numero di token della frase precedente nel dataset.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="6-qual-è-lo-scopo-di-una-funzione-di-raccolta-collate-function" 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="#6-qual-è-lo-scopo-di-una-funzione-di-raccolta-collate-function"><span><svg 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>6. Qual è lo scopo di una funzione di raccolta (collate function)?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Di assicurarsi che tutte le sequenze nel dataset abbiano la stessa lunghezza.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->Di raccogliere tutti i campioni in una batch.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Di preprocessare l'intero dataset<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Di troncare le sequenze nel dataset.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="7-cosa-succede-quando-una-classe-di-tipo-automodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato" 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="#7-cosa-succede-quando-una-classe-di-tipo-automodelforxxx-viene-istanziata-con-un-modello-di-linguaggio-pre-addestrato-come-bert-base-uncased--che-corrisponde-ad-un-compito-differente-rispetto-a-quello-per-cui-era-stato-addestrato"><span><svg 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>7. Cosa succede quando una classe di tipo AutoModelForXxx viene istanziata con un modello di linguaggio pre-addestrato (come bert-base-uncased ) che corrisponde ad un compito differente rispetto a quello per cui era stato addestrato?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Nulla, ma viene mostrato un avvertimento<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->La testa del modello pre-addestrato viene scartata e una nuova testa, appropriata per il compito, viene inserita al suo posto<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->La testa del modello pre-addestrato viene scartata<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Nulla, dato che il modello può comunque essere affinato per un compito differente.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="8-qual-è-lo-scopo-di-trainingarguments-" 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="#8-qual-è-lo-scopo-di-trainingarguments-"><span><svg 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>8. Qual è lo scopo di TrainingArguments ?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Contiene tutti gli iperparametri usati per l'addestramento e la valutazione con il <code>Trainer</code>.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->Specifica le dimensioni del modello.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Contiene soltanto gli iperparametri usati per la valutazione.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Contiene soltanto gli iperparametri usati per l'addestramento.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----> <!--[2--><h3 class="relative group"><a id="9-perché-si-dovrebbe-usare-la-libreria--accelerate" 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="#9-perché-si-dovrebbe-usare-la-libreria--accelerate"><span><svg 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>9. Perché si dovrebbe usare la libreria 🤗 Accelerate?</span></h3><!--]--><!----> <div><form><!--[--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"/> <!---->Fornisce l'accesso a modelli più veloci.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"/> <!---->Fornisce una API di alto livello, così non devo implementare il mio ciclo di addestramento.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"/> <!---->Permette ai nostri cicli di addestramento di venire eseguiti con strategie distribuite.<!----></label> <!--[-1--><!--]--><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"/> <!---->Fornisce altre funzioni di ottimizzazione.<!----></label> <!--[-1--><!--]--><!--]--> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled="">Submit</button> <!--[-1--><!--]--></div></form></div><!----><!--]--> <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/it/chapter3/6.mdx" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->

	<script>
	{
	__sveltekit_1mkvymp = {
	base: "/docs/course/pr_1306/it",
	assets: "/docs/course/pr_1306/it"
	};

	const element = document.currentScript.parentElement;

	Promise.all([
	import("/docs/course/pr_1306/it/_app/immutable/entry/start.CT6zZwAy.js"),
	import("/docs/course/pr_1306/it/_app/immutable/entry/app.DTrNdXKl.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 26],
	data: [null,null],
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 36.8 kB
Xet hash:: c8e8850c07d5fee96baff9d8f95cbc9225680d86e813df2e190ff4166320374e

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.