Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / course /pr_1114 /te /chapter1 /9.html

rtrm

30 days ago

download

raw

16 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"పక్షపాతం మరియు పరిమితులు","local":"bias-and-limitations","sections":[],"depth":1}">
	<link href="/docs/course/pr_1114/te/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/entry/start.72d37eca.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/scheduler.c9113122.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/singletons.9bb06688.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/index.a2483a6a.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/paths.ae945cd9.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/entry/app.628033b9.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/preload-helper.ad5b1238.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/index.582126dc.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/nodes/0.060129f0.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/nodes/13.bf93ef62.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.ab8cfe4e.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/CodeBlock.3f8cc1d9.js">
	<link rel="modulepreload" href="/docs/course/pr_1114/te/_app/immutable/chunks/CourseFloatingBanner.2ab9aa3a.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"పక్షపాతం మరియు పరిమితులు","local":"bias-and-limitations","sections":[],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <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 max-sm:gap-0.5 h-6 max-sm:h-5 px-2 max-sm:px-1.5 text-[11px] max-sm:text-[9px] 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"><svg class="w-3 h-3 max-sm:w-2.5 max-sm:h-2.5" 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-6 max-sm:h-5 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 w-3 h-3 max-sm:w-2.5 max-sm:h-2.5 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> </div> <h1 class="relative group"><a id="bias-and-limitations" 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="#bias-and-limitations"><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>పక్షపాతం మరియు పరిమితులు</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0" style=""><a href="https://discuss.huggingface.co/t/chapter-1-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/en/chapter1/section8.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/en/chapter1/section8.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-igcala">మీ ఉద్దేశ్యం ఒక ప్రీట్రైన్డ్ మోడల్ లేదా ఫైన్-ట్యూన్డ్ వెర్షన్‌ను ఉత్పత్తిలో ఉపయోగించాలనుకుంటే, దయచేసి ఈ మోడల్స్ శక్తివంతమైన సాధనాలు అయినప్పటికీ, వాటికి పరిమితులు ఉన్నాయని గుర్తుంచుకోండి. వీటిలో అతిపెద్దది ఏమిటంటే, పెద్ద మొత్తంలో డేటాపై ప్రీట్రైనింగ్‌ను ప్రారంభించడానికి, పరిశోధకులు తరచుగా వారు కనుగొనగలిగిన అన్ని కంటెంట్‌ను స్క్రాప్ చేస్తారు, ఇంటర్నెట్‌లో అందుబాటులో ఉన్న వాటిలో ఉత్తమమైనవి మరియు చెత్తైనవి రెండింటినీ తీసుకుంటారు.</p> <p data-svelte-h="svelte-nzm6o5">త్వరగా వివరించడానికి, BERT మోడల్‌తో <code>fill-mask</code> పైప్‌లైన్ ఉదాహరణకు తిరిగి వెళ్దాం:</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

	unmasker = pipeline(<span class="hljs-string">"fill-mask"</span>, model=<span class="hljs-string">"bert-base-uncased"</span>)
	result = unmasker(<span class="hljs-string">"This man works as a [MASK]."</span>)
	<span class="hljs-built_in">print</span>([r[<span class="hljs-string">"token_str"</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result])

	result = unmasker(<span class="hljs-string">"This woman works as a [MASK]."</span>)
	<span class="hljs-built_in">print</span>([r[<span class="hljs-string">"token_str"</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result])<!-- 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">'lawyer'</span>, <span class="hljs-string">'carpenter'</span>, <span class="hljs-string">'doctor'</span>, <span class="hljs-string">'waiter'</span>, <span class="hljs-string">'mechanic'</span>]
	[<span class="hljs-string">'nurse'</span>, <span class="hljs-string">'waitress'</span>, <span class="hljs-string">'teacher'</span>, <span class="hljs-string">'maid'</span>, <span class="hljs-string">'prostitute'</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-ngag6l">ఈ రెండు వాక్యాలలో తప్పిపోయిన పదాన్ని పూరించమని అడిగినప్పుడు, మోడల్ ఒకే ఒక లింగ-రహిత సమాధానం (waiter/waitress) మాత్రమే ఇస్తుంది. మిగిలినవి సాధారణంగా ఒక నిర్దిష్ట లింగంతో ముడిపడి ఉన్న వృత్తులు — మరియు అవును, “స్త్రీ” మరియు “పని”తో మోడల్ అనుబంధించే టాప్ 5 అవకాశాలలో prostitute చేరింది. BERT ఇంటర్నెట్ నుండి డేటాను స్క్రాప్ చేయడం ద్వారా నిర్మించబడని అరుదైన Transformer మోడల్స్‌లో ఒకటి అయినప్పటికీ ఇది జరుగుతుంది, బదులుగా తటస్థ డేటాను ఉపయోగించి (ఇది <a href="https://huggingface.co/datasets/wikipedia" rel="nofollow">English Wikipedia</a> మరియు <a href="https://huggingface.co/datasets/bookcorpus" rel="nofollow">BookCorpus</a> డేటాసెట్‌లపై శిక్షణ పొందింది).</p> <p data-svelte-h="svelte-9dwfr4">మీరు ఈ సాధనాలను ఉపయోగించినప్పుడు, మీరు ఉపయోగిస్తున్న అసలు మోడల్ చాలా సులభంగా సెక్సిస్ట్, జాతి వివక్షతో కూడిన లేదా హోమోఫోబిక్ కంటెంట్‌ను రూపొందించగలదని మీరు గుర్తుంచుకోవాలి. మీ డేటాపై మోడల్‌ను ఫైన్-ట్యూన్ చేయడం ఈ అంతర్గత పక్షపాతాన్ని తొలగించదు.</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/te/chapter1/9.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_tkqky = {
	assets: "/docs/course/pr_1114/te",
	base: "/docs/course/pr_1114/te",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/course/pr_1114/te/_app/immutable/entry/start.72d37eca.js"),
	import("/docs/course/pr_1114/te/_app/immutable/entry/app.628033b9.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 13],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 16 kB
Xet hash:: 239270ef6110e2e91df9c3df8540f875d955cf9d4385051b22637b485e1be5e9

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