domofon/basic-prt / fineweb-edu-v3 /_aggregate.json
domofon's picture
download
raw
2.27 kB
{
"dataset": "HuggingFaceFW/fineweb-edu",
"config": "data",
"split": "train",
"task": "fineweb-edu-v3",
"bucket_prefix": "fineweb-edu-v3",
"license": "ODC-BY",
"source_note": "FineWeb-Edu data/ config files 24-39 (continuation of arrow fineweb-edu-a [0,24); sample/10BT exhausted by fineweb-edu-v2)",
"ranges": [
{
"from_file": 24,
"to_file": 40
}
],
"shards": 56,
"rows": 6224248,
"tokens": 6651662405,
"bytes": 13303324810,
"files": [
"data-00000-of-00056.npy",
"data-00001-of-00056.npy",
"data-00002-of-00056.npy",
"data-00003-of-00056.npy",
"data-00004-of-00056.npy",
"data-00005-of-00056.npy",
"data-00006-of-00056.npy",
"data-00007-of-00056.npy",
"data-00008-of-00056.npy",
"data-00009-of-00056.npy",
"data-00010-of-00056.npy",
"data-00011-of-00056.npy",
"data-00012-of-00056.npy",
"data-00013-of-00056.npy",
"data-00014-of-00056.npy",
"data-00015-of-00056.npy",
"data-00016-of-00056.npy",
"data-00017-of-00056.npy",
"data-00018-of-00056.npy",
"data-00019-of-00056.npy",
"data-00020-of-00056.npy",
"data-00021-of-00056.npy",
"data-00022-of-00056.npy",
"data-00023-of-00056.npy",
"data-00024-of-00056.npy",
"data-00025-of-00056.npy",
"data-00026-of-00056.npy",
"data-00027-of-00056.npy",
"data-00028-of-00056.npy",
"data-00029-of-00056.npy",
"data-00030-of-00056.npy",
"data-00031-of-00056.npy",
"data-00032-of-00056.npy",
"data-00033-of-00056.npy",
"data-00034-of-00056.npy",
"data-00035-of-00056.npy",
"data-00036-of-00056.npy",
"data-00037-of-00056.npy",
"data-00038-of-00056.npy",
"data-00039-of-00056.npy",
"data-00040-of-00056.npy",
"data-00041-of-00056.npy",
"data-00042-of-00056.npy",
"data-00043-of-00056.npy",
"data-00044-of-00056.npy",
"data-00045-of-00056.npy",
"data-00046-of-00056.npy",
"data-00047-of-00056.npy",
"data-00048-of-00056.npy",
"data-00049-of-00056.npy",
"data-00050-of-00056.npy",
"data-00051-of-00056.npy",
"data-00052-of-00056.npy",
"data-00053-of-00056.npy",
"data-00054-of-00056.npy",
"data-00055-of-00056.npy"
],
"created": "2026-08-12T21:30:53.771646Z"
}

Xet Storage Details

Size:
2.27 kB
·
Xet hash:
fcc49a294c8ef2c4ce3a783a78efd3c3e7a8396249c62983c0caac232e00fae4

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