Buckets:

rtrm's picture
download
raw
9.38 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Datasets, kiểm tra nào!&quot;,&quot;local&quot;:&quot;-datasets-kiểm-tra-nào&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
<link href="/docs/course/pr_1114/vi/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/entry/start.8cb2bed2.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/scheduler.893fe8c9.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/singletons.19820476.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/index.bce52c8a.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/paths.f6a03f82.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/entry/app.15159ab9.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/preload-helper.9eab40ba.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/index.2d09ebb4.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/nodes/0.3a090b0c.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/each.e59479a4.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/nodes/40.19614d37.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.1dbb7ba5.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/CourseFloatingBanner.e3aeab73.js">
<link rel="modulepreload" href="/docs/course/pr_1114/vi/_app/immutable/chunks/DocNotebookDropdown.c43deb26.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;🤗 Datasets, kiểm tra nào!&quot;,&quot;local&quot;:&quot;-datasets-kiểm-tra-nào&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 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="-datasets-kiểm-tra-nào" 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="#-datasets-kiểm-tra-nào"><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>🤗 Datasets, kiểm tra nào!</span></h1> <div class="flex space-x-1 absolute z-10 right-0 top-0" style=""><a href="https://discuss.huggingface.co/t/chapter-5-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-ql1gi1">Chà, đó là một chuyến tham quan khá thú vị qua thư viện 🤗 Datasets - chúc mừng bạn đã đi được xa như vậy! Với kiến thức bạn đã thu được từ chương này, bạn sẽ có thể:</p> <ul data-svelte-h="svelte-lcyxed"><li>Tải bộ dữ liệu từ bất kỳ đâu, có thể là Hugging Face Hub, máy tính xách tay của bạn hoặc máy chủ từ xa tại công ty của bạn.</li> <li>Xoá dữ liệu của bạn bằng cách sử dụng kết hợp các hàm <code>Dataset.map()</code><code>Dataset.filter()</code>.</li> <li>Chuyển đổi nhanh chóng giữa các định dạng dữ liệu như Pandas và NumPy bằng cách sử dụng <code>Dataset.set_format()</code>.</li> <li>Tạo tập dữ liệu của riêng bạn và đẩy nó vào Hugging Face Hub.</li> <li>Nhúng tài liệu của bạn bằng mô hình Transformer và xây dựng công cụ tìm kiếm ngữ nghĩa bằng FAISS.</li></ul> <p data-svelte-h="svelte-x8m57q">Trong <a href="/course/chapter7">Chương 7</a>, chúng ta sẽ sử dụng tốt tất cả những điều này khi ta đi sâu vào các tác vụ NLP cốt lõi mà các mô hình Transformer rất phù hợp. Tuy nhiên, trước khi vượt lên phía trước, hãy đưa kiến thức của bạn về 🤗 Datasets vào một bài kiểm tra nhanh!</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/vi/chapter5/7.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_11wxnfb = {
assets: "/docs/course/pr_1114/vi",
base: "/docs/course/pr_1114/vi",
env: {}
};
const element = document.currentScript.parentElement;
const data = [null,null];
Promise.all([
import("/docs/course/pr_1114/vi/_app/immutable/entry/start.8cb2bed2.js"),
import("/docs/course/pr_1114/vi/_app/immutable/entry/app.15159ab9.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 40],
data,
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
9.38 kB
·
Xet hash:
ec219b3b3a71241328fa3d5287b0656ededb6686e48dfe4f76ec17f2b22f060a

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