Buckets:

rtrm's picture
download
raw
10.8 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;本章简介&quot;,&quot;local&quot;:&quot;本章简介&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/course/pr_1213/zh-CN/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/entry/start.e9a4ad0c.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/scheduler.893fe8c9.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/singletons.7c7a7de8.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/index.bce52c8a.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/paths.59f00eb6.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/entry/app.a615bcac.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/preload-helper.00a0cfc8.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/index.2d09ebb4.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/nodes/0.d5282dd8.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/nodes/15.764095f1.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.fcdcb9db.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/CourseFloatingBanner.e3aeab73.js">
<link rel="modulepreload" href="/docs/course/pr_1213/zh-CN/_app/immutable/chunks/DocNotebookDropdown.c43deb26.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;本章简介&quot;,&quot;local&quot;:&quot;本章简介&quot;,&quot;sections&quot;:[],&quot;depth&quot;: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 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> </div> <h1 class="relative group"><a id="本章简介" 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="#本章简介"><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>本章简介</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0" style=""><a href="https://discuss.huggingface.co/t/chapter-2-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> </div> <p data-svelte-h="svelte-kzps0h">正如你在 <a href="/course/chapter1">第一章</a> ,中看到的那样,Transformers 模型通常规模庞大。包含数以百万计到数千万计数十亿的参数,训练和部署这些模型是一项复杂的任务。再者,新模型的推出几乎日新月异,而每种模型都有其独特的实现方式,尝试全部模型绝非易事。</p> <p data-svelte-h="svelte-1n7vpa">🤗 Transformers 库应运而生,就是为了解决这个问题。它的目标是提供一个统一的 API 接口,通过它可以加载、训练和保存任何 Transformer 模型。该库的主要特点有:</p> <ul data-svelte-h="svelte-gz80c6"><li><strong>易于使用</strong>:仅需两行代码,就能下载、加载并使用先进的 NLP 模型进行推理。</li> <li><strong>灵活</strong>:在本质上,所有的模型都是简单的 PyTorch nn.Module 或 TensorFlow tf.keras.Model 类,并可像在各自的机器学习(ML)框架中处理其他模型一样处理它们。</li> <li><strong>简单</strong>:该库几乎没有进行任何抽象化。🤗 Transformers 库一个核心概念是“全在一个文件中”:模型的前向传播完全在一个文件中定义,这使得代码本身易于理解和修改。</li></ul> <p data-svelte-h="svelte-qyb0i3">最后一个特性使🤗 Transformers 与其他 ML 库截然不同。模型并非建立在跨越多个代码文件共享的模块上;相反,每一个模型都有自己的层次结构。除了使模型更加容易接受和更容易理解,这还允许你轻松地在一个模型上实验,而且不影响其他模型。</p> <p data-svelte-h="svelte-6emoa7">本章将从一个端到端(从输入端到输出端)的示例开始,在该示例中,我们一起使用模型和 tokenizer 来复刻 <a href="/course/chapter1">第一章</a> 中看到的 <code>pipeline()</code> 函数。接下来,我们将讨论 <code>Model</code> API:我们将深入研究 <code>Model</code> 类和 <code>Config</code> 类,并向你展示如何加载模型,以及它如何将输入处理为输出。</p> <p data-svelte-h="svelte-1croyj">然后我们来看看 <code>tokenizer</code> API,它是 <code>pipeline()</code> 函数的另一个重要组成部分。在 <code>pipeline()</code><code>Tokenizer</code> 负责第一步和最后一步的处理,将文本转换到神经网络的输入,以及在需要时将其转换回文本。最后,我们将向你展示如何处理将多个句子整理为一个 batch 发送给模型,然后我们将更深入地研究 <code>tokenizer()</code> 函数。</p> <blockquote class="tip" data-svelte-h="svelte-fdmg1t"><p>⚠️ 为了充分利用 Model Hub 和🤗 Transformers 提供的所有功能,我们建议你<a href="https://huggingface.co/join">创建一个账户</a></p></blockquote> <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-CN/chapter2/1.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_k5k00v = {
assets: "/docs/course/pr_1213/zh-CN",
base: "/docs/course/pr_1213/zh-CN",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/course/pr_1213/zh-CN/_app/immutable/entry/start.e9a4ad0c.js"),
import("/docs/course/pr_1213/zh-CN/_app/immutable/entry/app.a615bcac.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 15],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
10.8 kB
·
Xet hash:
966f0c15e23ebd35c2890928c268b8315d8dce368eb14660579b492d6c2486dd

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