Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Data files Configuration","local":"data-files-configuration","sections":[{"title":"What are splits and subsets?","local":"what-are-splits-and-subsets","sections":[],"depth":2},{"title":"Automatic splits detection","local":"automatic-splits-detection","sections":[],"depth":2},{"title":"Manual splits and subsets configuration","local":"manual-splits-and-subsets-configuration","sections":[],"depth":2},{"title":"Supported file formats","local":"supported-file-formats","sections":[{"title":"Dataset Viewer size-limit errors ( TooBigContentError )","local":"dataset-viewer-size-limit-errors--toobigcontenterror-","sections":[],"depth":3}],"depth":2},{"title":"Image, Audio and Video datasets","local":"image-audio-and-video-datasets","sections":[],"depth":2}],"depth":1}"> | |
| <link href="/docs/hub/pr_2437/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/entry/start.5e3ed1fd.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/scheduler.258d2a4d.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/singletons.2d0c91e1.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/index.c8b82093.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/paths.d360121b.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/entry/app.93e7704b.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/preload-helper.a4507a26.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/index.421344fd.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/nodes/0.bedbef6e.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/each.e59479a4.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/nodes/30.818ce222.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/CopyLLMTxtMenu.9c2a67a1.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.9bb92958.js"> | |
| <link rel="modulepreload" href="/docs/hub/pr_2437/en/_app/immutable/chunks/CodeBlock.619ec4e3.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Data files Configuration","local":"data-files-configuration","sections":[{"title":"What are splits and subsets?","local":"what-are-splits-and-subsets","sections":[],"depth":2},{"title":"Automatic splits detection","local":"automatic-splits-detection","sections":[],"depth":2},{"title":"Manual splits and subsets configuration","local":"manual-splits-and-subsets-configuration","sections":[],"depth":2},{"title":"Supported file formats","local":"supported-file-formats","sections":[{"title":"Dataset Viewer size-limit errors ( TooBigContentError )","local":"dataset-viewer-size-limit-errors--toobigcontenterror-","sections":[],"depth":3}],"depth":2},{"title":"Image, Audio and Video datasets","local":"image-audio-and-video-datasets","sections":[],"depth":2}],"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 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="data-files-configuration" 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="#data-files-configuration"><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>Data files Configuration</span></h1> <p data-svelte-h="svelte-1sicc2g">There are no constraints on how to structure dataset repositories.</p> <p data-svelte-h="svelte-rffpu1">However, if you want the Dataset Viewer to show certain data files, or to separate your dataset in train/validation/test splits, you need to structure your dataset accordingly. | |
| Often it is as simple as naming your data files according to their split names, e.g. <code>train.csv</code> and <code>test.csv</code>.</p> <h2 class="relative group"><a id="what-are-splits-and-subsets" 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="#what-are-splits-and-subsets"><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>What are splits and subsets?</span></h2> <p data-svelte-h="svelte-1scij8h">Machine learning datasets typically have splits and may also have subsets. A dataset is generally made of <em>splits</em> (e.g. <code>train</code> and <code>test</code>) that are used during different stages of training and evaluating a model. A <em>subset</em> (also called <em>configuration</em>) is a sub-dataset contained within a larger dataset. Subsets are especially common in multilingual speech datasets where there may be a different subset for each language. If you’re interested in learning more about splits and subsets, check out the <a href="/docs/datasets-server/configs_and_splits">Splits and subsets</a> guide!</p> <p data-svelte-h="svelte-1p3cuco"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/split-configs-server.gif" alt="split-configs-server"></p> <h2 class="relative group"><a id="automatic-splits-detection" 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="#automatic-splits-detection"><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>Automatic splits detection</span></h2> <p data-svelte-h="svelte-1l3jl1k">Splits are automatically detected based on file and directory names. For example, this is a dataset with <code>train</code>, <code>test</code>, and <code>validation</code> splits:</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 -->my_dataset_repository/ | |
| ├── README.md | |
| ├── train.<span class="hljs-built_in">csv</span> | |
| ├── test.<span class="hljs-built_in">csv</span> | |
| └── validation.<span class="hljs-built_in">csv</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1gvdkiz">To structure your dataset by naming your data files or directories according to their split names, see the <a href="./datasets-file-names-and-splits">File names and splits</a> documentation and the <a href="https://huggingface.co/collections/datasets-examples/file-names-and-splits-655e28af4471bd95709eb135" rel="nofollow">companion collection of example datasets</a>.</p> <h2 class="relative group"><a id="manual-splits-and-subsets-configuration" 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="#manual-splits-and-subsets-configuration"><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>Manual splits and subsets configuration</span></h2> <p data-svelte-h="svelte-irk0xr">You can choose the data files to show in the Dataset Viewer for your dataset using YAML. | |
| It is useful if you want to specify which file goes into which split manually.</p> <p data-svelte-h="svelte-24qwdr">You can also define multiple subsets for your dataset, and pass dataset building parameters (e.g. the separator to use for CSV files).</p> <p data-svelte-h="svelte-acor93">Here is an example of a configuration defining a subset called “benchmark” with a <code>test</code> split.</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-attr">configs:</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-attr">config_name:</span> <span class="hljs-string">benchmark</span> | |
| <span class="hljs-attr">data_files:</span> | |
| <span class="hljs-bullet">-</span> <span class="hljs-attr">split:</span> <span class="hljs-string">test</span> | |
| <span class="hljs-attr">path:</span> <span class="hljs-string">benchmark.csv</span><!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-1bzrp3h">See the documentation on <a href="./datasets-manual-configuration">Manual configuration</a> for more information. Look also to the <a href="https://huggingface.co/collections/datasets-examples/manual-configuration-655e293cea26da0acab95b87" rel="nofollow">example datasets</a>.</p> <h2 class="relative group"><a id="supported-file-formats" 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="#supported-file-formats"><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>Supported file formats</span></h2> <p data-svelte-h="svelte-13m965x">See the <a href="./datasets-adding#file-formats">File formats</a> doc page to find the list of supported formats and recommendations for your dataset. If your dataset uses CSV or TSV files, you can find more information in the <a href="https://huggingface.co/collections/datasets-examples/format-csv-and-tsv-655f681cb9673a4249cccb3d" rel="nofollow">example datasets</a>.</p> <h3 class="relative group"><a id="dataset-viewer-size-limit-errors--toobigcontenterror-" 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="#dataset-viewer-size-limit-errors--toobigcontenterror-"><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>Dataset Viewer size-limit errors ( TooBigContentError )</span></h3> <p data-svelte-h="svelte-1h9mzqt">If you see <code>Error code: TooBigContentError</code>, then the dataset viewer could not read a preview within its limits. Common messages include <code>Parquet error: Scan size limit exceeded</code> and <code>The size of the content of the first rows exceeds the maximum supported size</code>.</p> <p data-svelte-h="svelte-r68gwu">What you can do:</p> <ul data-svelte-h="svelte-aciz5b"><li>For Parquet files, use smaller row groups and include a page index (<code>write_page_index=True</code>) so the Viewer can read only what it needs.</li> <li>Avoid very large values in the first rows (very long strings, large JSON blobs, base64 payloads). Move large payloads to separate files when possible.</li> <li>Split very large files into smaller shards or splits, then re-upload.</li> <li>If the issue remains, review <a href="./datasets-viewer-configure">Configure the Dataset Viewer</a> and open a discussion on your dataset page with the full error text.</li></ul> <h2 class="relative group"><a id="image-audio-and-video-datasets" 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="#image-audio-and-video-datasets"><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>Image, Audio and Video datasets</span></h2> <p data-svelte-h="svelte-cp92ju">For image/audio/video classification datasets, you can also use directories to name the image/audio/video classes. | |
| And if your images/audio/video files have metadata (e.g. captions, bounding boxes, transcriptions, etc.), you can have metadata files next to them.</p> <p data-svelte-h="svelte-1s3m8si">We provide two guides that you can check out:</p> <ul data-svelte-h="svelte-1uc6vgs"><li><a href="./datasets-image">How to create an image dataset</a> (<a href="https://huggingface.co/collections/datasets-examples/image-dataset-6568e7cf28639db76eb92d65" rel="nofollow">example datasets</a>)</li> <li><a href="./datasets-audio">How to create an audio dataset</a> (<a href="https://huggingface.co/collections/datasets-examples/audio-dataset-66aca0b73e8f69e3d069e607" rel="nofollow">example datasets</a>)</li> <li><a href="./datasets-video">How to create a video dataset</a></li></ul> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/hub-docs/blob/main/docs/hub/datasets-data-files-configuration.md" 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_ummgov = { | |
| assets: "/docs/hub/pr_2437/en", | |
| base: "/docs/hub/pr_2437/en", | |
| env: {} | |
| }; | |
| const element = document.currentScript.parentElement; | |
| const data = [null,null]; | |
| Promise.all([ | |
| import("/docs/hub/pr_2437/en/_app/immutable/entry/start.5e3ed1fd.js"), | |
| import("/docs/hub/pr_2437/en/_app/immutable/entry/app.93e7704b.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 30], | |
| data, | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 23.2 kB
- Xet hash:
- 589386d47fd32a34b4b2e6403a5745aee74af48a52c06913734ba19f55394330
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.