Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers /main /zh /fast_tokenizers.html

rtrm

28 days ago

download

raw

15.7 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"使用 🤗 Tokenizers 中的分词器","local":"使用--tokenizers-中的分词器","sections":[{"title":"直接从分词器对象加载","local":"直接从分词器对象加载","sections":[],"depth":2},{"title":"从 JSON 文件加载","local":"从-json-文件加载","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/transformers/main/zh/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/entry/start.a61b9c50.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/scheduler.9991993c.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/singletons.2822fe91.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/index.02cfeb18.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/paths.d66588b4.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/entry/app.99775688.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/index.7fc9a5e7.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/nodes/0.f4c5a5c1.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/nodes/11.07bd7d46.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/CodeBlock.e11cba92.js">
	<link rel="modulepreload" href="/docs/transformers/main/zh/_app/immutable/chunks/EditOnGithub.84ab7f0e.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"使用 🤗 Tokenizers 中的分词器","local":"使用--tokenizers-中的分词器","sections":[{"title":"直接从分词器对象加载","local":"直接从分词器对象加载","sections":[],"depth":2},{"title":"从 JSON 文件加载","local":"从-json-文件加载","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <h1 class="relative group"><a id="使用--tokenizers-中的分词器" 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="#使用--tokenizers-中的分词器"><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>使用 🤗 Tokenizers 中的分词器</span></h1> <p data-svelte-h="svelte-1xn4qlv"><a href="/docs/transformers/main/zh/main_classes/tokenizer#transformers.PreTrainedTokenizerFast">PreTrainedTokenizerFast</a> 依赖于 <a href="https://huggingface.co/docs/tokenizers" rel="nofollow">🤗 Tokenizers</a> 库。从 🤗 Tokenizers 库获得的分词器可以被轻松地加载到 🤗 Transformers 中。</p> <p data-svelte-h="svelte-opvc5k">在了解具体内容之前，让我们先用几行代码创建一个虚拟的分词器：</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers <span class="hljs-keyword">import</span> Tokenizer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.models <span class="hljs-keyword">import</span> BPE
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.trainers <span class="hljs-keyword">import</span> BpeTrainer
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> tokenizers.pre_tokenizers <span class="hljs-keyword">import</span> Whitespace

	<span class="hljs-meta">>>> </span>tokenizer = Tokenizer(BPE(unk_token=<span class="hljs-string">"[UNK]"</span>))
	<span class="hljs-meta">>>> </span>trainer = BpeTrainer(special_tokens=[<span class="hljs-string">"[UNK]"</span>, <span class="hljs-string">"[CLS]"</span>, <span class="hljs-string">"[SEP]"</span>, <span class="hljs-string">"[PAD]"</span>, <span class="hljs-string">"[MASK]"</span>])

	<span class="hljs-meta">>>> </span>tokenizer.pre_tokenizer = Whitespace()
	<span class="hljs-meta">>>> </span>files = [...]
	<span class="hljs-meta">>>> </span>tokenizer.train(files, trainer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-17x9tu2">现在，我们拥有了一个针对我们定义的文件进行训练的分词器。我们可以在当前运行时中继续使用它，或者将其保存到一个 JSON 文件以供将来重复使用。</p> <h2 class="relative group"><a id="直接从分词器对象加载" 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="#直接从分词器对象加载"><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>直接从分词器对象加载</span></h2> <p data-svelte-h="svelte-o65hyz">让我们看看如何利用 🤗 Transformers 库中的这个分词器对象。<a href="/docs/transformers/main/zh/main_classes/tokenizer#transformers.PreTrainedTokenizerFast">PreTrainedTokenizerFast</a> 类允许通过接受已实例化的 <em>tokenizer</em> 对象作为参数，进行轻松实例化：</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> PreTrainedTokenizerFast

	<span class="hljs-meta">>>> </span>fast_tokenizer = PreTrainedTokenizerFast(tokenizer_object=tokenizer)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-tb93lc">现在可以使用这个对象，使用 🤗 Transformers 分词器共享的所有方法！前往<a href="main_classes/tokenizer">分词器页面</a>了解更多信息。</p> <h2 class="relative group"><a id="从-json-文件加载" 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="#从-json-文件加载"><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>从 JSON 文件加载</span></h2> <p data-svelte-h="svelte-lr3arf">为了从 JSON 文件中加载分词器，让我们先保存我们的分词器：</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span>tokenizer.save(<span class="hljs-string">"tokenizer.json"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-x5pc4q">我们保存此文件的路径可以通过 <code>tokenizer_file</code> 参数传递给 <a href="/docs/transformers/main/zh/main_classes/tokenizer#transformers.PreTrainedTokenizerFast">PreTrainedTokenizerFast</a> 初始化方法：</p> <div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5 text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> PreTrainedTokenizerFast

	<span class="hljs-meta">>>> </span>fast_tokenizer = PreTrainedTokenizerFast(tokenizer_file=<span class="hljs-string">"tokenizer.json"</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-tb93lc">现在可以使用这个对象，使用 🤗 Transformers 分词器共享的所有方法！前往<a href="main_classes/tokenizer">分词器页面</a>了解更多信息。</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/transformers/blob/main/docs/source/zh/fast_tokenizers.md" target="_blank"><span data-svelte-h="svelte-1kd6by1"><</span> <span data-svelte-h="svelte-x0xyl0">></span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a> <p></p>

	<script>
	{
	__sveltekit_173uja2 = {
	assets: "/docs/transformers/main/zh",
	base: "/docs/transformers/main/zh",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/transformers/main/zh/_app/immutable/entry/start.a61b9c50.js"),
	import("/docs/transformers/main/zh/_app/immutable/entry/app.99775688.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 11],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 15.7 kB
Xet hash:: e4974579a436442107e72d2ad4ffaef1a8240bd2ed17066944192df4c501cc04

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