Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / course /pr_1021 /zh-TW /chapter7 /9.html
rtrm's picture
rtrm
download
raw
39.8 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;End-of-chapter quiz&quot;,&quot;local&quot;:&quot;end-of-chapter-quiz&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;1.下列哪個任務可以被框定為令牌分類問題？&quot;,&quot;local&quot;:&quot;1下列哪個任務可以被框定為令牌分類問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;2.令牌分類預處理的哪一部分與其他預處理管道不同？&quot;,&quot;local&quot;:&quot;2令牌分類預處理的哪一部分與其他預處理管道不同&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;3.當我們對標記分類問題中的單詞進行標記並希望標記時，會出現什麼問題？&quot;,&quot;local&quot;:&quot;3當我們對標記分類問題中的單詞進行標記並希望標記時會出現什麼問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;4.“領域適應”是什麼意思？&quot;,&quot;local&quot;:&quot;4領域適應是什麼意思&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;5.掩碼語言建模問題中的標籤是什麼？&quot;,&quot;local&quot;:&quot;5掩碼語言建模問題中的標籤是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;6.這些任務中的哪一個可以看作是一個順序到順序的問題？&quot;,&quot;local&quot;:&quot;6這些任務中的哪一個可以看作是一個順序到順序的問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;7.對於序列到序列的問題，預處理數據的正確方法是什麼？&quot;,&quot;local&quot;:&quot;7對於序列到序列的問題預處理數據的正確方法是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;8.為什麼序列到序列問題有一個特定的“培訓者”子類？&quot;,&quot;local&quot;:&quot;8為什麼序列到序列問題有一個特定的培訓者子類&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;9.為什麼在 Transformer 模型上調用“ compile ()”時通常不需要指定損失？&quot;,&quot;local&quot;:&quot;9為什麼在-transformer-模型上調用-compile-時通常不需要指定損失&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;10.你應該在什麼時候預先訓練一個新的模型？&quot;,&quot;local&quot;:&quot;10你應該在什麼時候預先訓練一個新的模型&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;11.為什麼在大量的文本上預先訓練一個語言模型是很容易的呢？&quot;,&quot;local&quot;:&quot;11為什麼在大量的文本上預先訓練一個語言模型是很容易的呢&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;12.問答任務的預處理數據時，主要的挑戰是什麼？&quot;,&quot;local&quot;:&quot;12問答任務的預處理數據時主要的挑戰是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;13.問題回答中的後處理通常是怎樣進行的？&quot;,&quot;local&quot;:&quot;13問題回答中的後處理通常是怎樣進行的&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}">
 <link href="/docs/course/pr_1021/zh-TW/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/entry/start.41617dd6.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/scheduler.37c15a92.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/singletons.75b420cf.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/index.18351ede.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/paths.241f8580.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/entry/app.89205ec4.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/index.2bf4358c.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/nodes/0.72d34023.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/each.e59479a4.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/nodes/62.30d27899.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/Question.668688bc.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/FrameworkSwitchCourse.8d4d4ab6.js">
 <link rel="modulepreload" href="/docs/course/pr_1021/zh-TW/_app/immutable/chunks/getInferenceSnippets.ebf8be91.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;End-of-chapter quiz&quot;,&quot;local&quot;:&quot;end-of-chapter-quiz&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;1.下列哪個任務可以被框定為令牌分類問題？&quot;,&quot;local&quot;:&quot;1下列哪個任務可以被框定為令牌分類問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;2.令牌分類預處理的哪一部分與其他預處理管道不同？&quot;,&quot;local&quot;:&quot;2令牌分類預處理的哪一部分與其他預處理管道不同&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;3.當我們對標記分類問題中的單詞進行標記並希望標記時，會出現什麼問題？&quot;,&quot;local&quot;:&quot;3當我們對標記分類問題中的單詞進行標記並希望標記時會出現什麼問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;4.“領域適應”是什麼意思？&quot;,&quot;local&quot;:&quot;4領域適應是什麼意思&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;5.掩碼語言建模問題中的標籤是什麼？&quot;,&quot;local&quot;:&quot;5掩碼語言建模問題中的標籤是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;6.這些任務中的哪一個可以看作是一個順序到順序的問題？&quot;,&quot;local&quot;:&quot;6這些任務中的哪一個可以看作是一個順序到順序的問題&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;7.對於序列到序列的問題，預處理數據的正確方法是什麼？&quot;,&quot;local&quot;:&quot;7對於序列到序列的問題預處理數據的正確方法是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;8.為什麼序列到序列問題有一個特定的“培訓者”子類？&quot;,&quot;local&quot;:&quot;8為什麼序列到序列問題有一個特定的培訓者子類&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;9.為什麼在 Transformer 模型上調用“ compile ()”時通常不需要指定損失？&quot;,&quot;local&quot;:&quot;9為什麼在-transformer-模型上調用-compile-時通常不需要指定損失&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;10.你應該在什麼時候預先訓練一個新的模型？&quot;,&quot;local&quot;:&quot;10你應該在什麼時候預先訓練一個新的模型&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;11.為什麼在大量的文本上預先訓練一個語言模型是很容易的呢？&quot;,&quot;local&quot;:&quot;11為什麼在大量的文本上預先訓練一個語言模型是很容易的呢&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;12.問答任務的預處理數據時，主要的挑戰是什麼？&quot;,&quot;local&quot;:&quot;12問答任務的預處理數據時主要的挑戰是什麼&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;13.問題回答中的後處理通常是怎樣進行的？&quot;,&quot;local&quot;:&quot;13問題回答中的後處理通常是怎樣進行的&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END --> <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> <h1 class="relative group"><a id="end-of-chapter-quiz" 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="#end-of-chapter-quiz"><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>End-of-chapter quiz</span></h1> <p data-svelte-h="svelte-19og2hy">Let’s test what you learned in this chapter!</p> <h3 class="relative group"><a id="1下列哪個任務可以被框定為令牌分類問題" 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下列哪個任務可以被框定為令牌分類問題"><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>1.下列哪個任務可以被框定為令牌分類問題？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->找出句子中的語法成分。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->判斷一個句子的語法是否正確。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->找出句子中提到的人物。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->找到一個句子中能夠回答問題的詞組。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="2令牌分類預處理的哪一部分與其他預處理管道不同" 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令牌分類預處理的哪一部分與其他預處理管道不同"><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>2.令牌分類預處理的哪一部分與其他預處理管道不同？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->當我們在數據集上運行一個模型，並獲得該數據集中每個樣本的預測時。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->在應用截斷/填充時，我們需要確保將標籤截斷或填充到與輸入相同的大小。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->沒有必要做任何事情，課文已經被標記了。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->因為互聯網上有大量的文本<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="3當我們對標記分類問題中的單詞進行標記並希望標記時會出現什麼問題" 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當我們對標記分類問題中的單詞進行標記並希望標記時會出現什麼問題"><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>3.當我們對標記分類問題中的單詞進行標記並希望標記時，會出現什麼問題？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->標記器添加了特殊的標記，我們沒有為他們的標籤。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->每個單詞可以產生幾個標記，所以我們最終得到的標記比標籤多。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->因為目標是按順序排列的文本問題<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="4領域適應是什麼意思" 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領域適應是什麼意思"><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>4.“領域適應”是什麼意思？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->因為模型的內部損耗輸出是默認使用的<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->當我們在數據集上訓練模型時。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->當我們對一個新的數據集微調一個預先訓練好的模型時，它給出的預測更適合這個數據集<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->當我們將錯誤分類的樣本添加到數據集中，使得我們的模型更加健壯。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="5掩碼語言建模問題中的標籤是什麼" 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掩碼語言建模問題中的標籤是什麼"><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>5.掩碼語言建模問題中的標籤是什麼？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->輸入句子中的一些標記是隨機屏蔽的，標籤是原始輸入標記。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->輸入句子中的一些標記是隨機屏蔽的，標籤是原始的輸入標記，向左移動。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->輸入句子中的一些標記是隨機屏蔽的，標籤是這個句子是肯定的還是否定的。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->兩個句子中的一些標記是隨機屏蔽的，標籤是兩個句子是否相似。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="6這些任務中的哪一個可以看作是一個順序到順序的問題" 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這些任務中的哪一個可以看作是一個順序到順序的問題"><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>6.這些任務中的哪一個可以看作是一個順序到順序的問題？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->撰寫長文檔的簡短評論<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->回答有關文件的問題<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->我們使用 < code >-100 </code > 來標記特殊標記。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->修正我侄子/朋友發來的信息，使它們用正確的英語<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="7對於序列到序列的問題預處理數據的正確方法是什麼" 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對於序列到序列的問題預處理數據的正確方法是什麼"><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>7.對於序列到序列的問題，預處理數據的正確方法是什麼？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->輸入和目標必須一起發送到標記器，其中包括 < code > input = ... </code > 和 < code > target = ... </code > 。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->輸入和目標都必須在對標記器的兩個獨立調用中進行預處理。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->因為我們在訓練之後計算度量<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->輸入必須發送到標記器，目標也是如此，但需要使用特殊的上下文管理器。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="8為什麼序列到序列問題有一個特定的培訓者子類" 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為什麼序列到序列問題有一個特定的培訓者子類"><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>8.為什麼序列到序列問題有一個特定的“培訓者”子類？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->因為序列到序列問題使用自定義丟失，所以忽略設置為 < code >-100 </code > 的標籤<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->當您擁有大量可用數據時，即使有一個經過預先訓練的模型可以處理這些數據<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->文本是作為單詞給出的，所以我們只需要應用子詞的標記。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->因為我們在序列到序列問題中使用了兩個模型<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="10你應該在什麼時候預先訓練一個新的模型" 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="#10你應該在什麼時候預先訓練一個新的模型"><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>10.你應該在什麼時候預先訓練一個新的模型？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->當您的特定語言沒有經過預先訓練的模型時<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->當您有大量可用的數據時，即使有一個經過訓練的模型可以處理這些數據<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->當你擔心你所使用的預先訓練過的模型的偏差時<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->當可用的預先訓練好的模型還不夠好的時候<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="11為什麼在大量的文本上預先訓練一個語言模型是很容易的呢" 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="#11為什麼在大量的文本上預先訓練一個語言模型是很容易的呢"><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>11.為什麼在大量的文本上預先訓練一個語言模型是很容易的呢？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->當你擔心你所使用的預先訓練的模型的偏差時<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->因為預訓練目標不需要人工標記數據<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->因為變形金剛庫只需要幾行代碼就可以開始培訓<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="12問答任務的預處理數據時主要的挑戰是什麼" 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="#12問答任務的預處理數據時主要的挑戰是什麼"><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>12.問答任務的預處理數據時，主要的挑戰是什麼？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->你需要對輸入進行標記。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->你需要處理非常長的上下文，這些上下文提供了一些訓練特性，這些特性可能有也可能沒有答案。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->您需要將問題的答案以及輸入標記化。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->從文本中的答案範圍中，您必須在標記化的輸入中找到開始和結束標記。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </div></form></div> <h3 class="relative group"><a id="13問題回答中的後處理通常是怎樣進行的" 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="#13問題回答中的後處理通常是怎樣進行的"><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>13.問題回答中的後處理通常是怎樣進行的？</span></h3> <div><form><label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="0"> <!-- HTML_TAG_START -->模型給出了答案的開始位置和結束位置，您只需要解碼相應的標記跨度。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="1"> <!-- HTML_TAG_START -->該模型為每個由一個示例創建的特性提供了答案的開始和結束位置，您只需要解碼分數最高的那個特性中相應的記號跨度。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="2"> <!-- HTML_TAG_START -->該模型為每個示例創建的特性提供了答案的開始和結束位置，您只需將它們與上下文中得分最高的特性的跨度相匹配。<!-- HTML_TAG_END --></label> <label class="block"><input autocomplete="off" class="form-input -mt-1.5 mr-2" name="choice" type="checkbox" value="3"> <!-- HTML_TAG_START -->模型生成一個答案，你只需要解碼它。<!-- HTML_TAG_END --></label> <div class="flex flex-row items-center mt-3"><button class="btn px-4 mr-4" type="submit" disabled>Submit</button> </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/zh-TW/chapter7/9.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>
<script>
 {
 __sveltekit_kgz26w = {
 assets: "/docs/course/pr_1021/zh-TW",
 base: "/docs/course/pr_1021/zh-TW",
 env: {}
 };
 const element = document.currentScript.parentElement;
 const data = [null,null];
 Promise.all([
 import("/docs/course/pr_1021/zh-TW/_app/immutable/entry/start.41617dd6.js"),
 import("/docs/course/pr_1021/zh-TW/_app/immutable/entry/app.89205ec4.js")
 ]).then(([kit, app]) => {
 kit.start(app, element, {
 node_ids: [0, 62],
 data,
 form: null,
 error: null
 });
 });
 }
 </script>

Xet Storage Details

Size:
39.8 kB
·
Xet hash:
8e2bb0d2510680c37b4e2fd48e4fb422bb7ebd8b22bef73cf4f89aedec002508

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