domofon/datasets / dolma3-cc-v2 /_aggregate.json
domofon's picture
download
raw
2.55 kB
{
"engine": "tokforge",
"prefix": "dolma3-cc-v2",
"corpus": "dolma3",
"version": "v2",
"shards": 70,
"docs": 21947160,
"tokens": 8630697760,
"bytes": 17261395520,
"files": [
"data-00000-of-00070.npy",
"data-00001-of-00070.npy",
"data-00002-of-00070.npy",
"data-00003-of-00070.npy",
"data-00004-of-00070.npy",
"data-00005-of-00070.npy",
"data-00006-of-00070.npy",
"data-00007-of-00070.npy",
"data-00008-of-00070.npy",
"data-00009-of-00070.npy",
"data-00010-of-00070.npy",
"data-00011-of-00070.npy",
"data-00012-of-00070.npy",
"data-00013-of-00070.npy",
"data-00014-of-00070.npy",
"data-00015-of-00070.npy",
"data-00016-of-00070.npy",
"data-00017-of-00070.npy",
"data-00018-of-00070.npy",
"data-00019-of-00070.npy",
"data-00020-of-00070.npy",
"data-00021-of-00070.npy",
"data-00022-of-00070.npy",
"data-00023-of-00070.npy",
"data-00024-of-00070.npy",
"data-00025-of-00070.npy",
"data-00026-of-00070.npy",
"data-00027-of-00070.npy",
"data-00028-of-00070.npy",
"data-00029-of-00070.npy",
"data-00030-of-00070.npy",
"data-00031-of-00070.npy",
"data-00032-of-00070.npy",
"data-00033-of-00070.npy",
"data-00034-of-00070.npy",
"data-00035-of-00070.npy",
"data-00036-of-00070.npy",
"data-00037-of-00070.npy",
"data-00038-of-00070.npy",
"data-00039-of-00070.npy",
"data-00040-of-00070.npy",
"data-00041-of-00070.npy",
"data-00042-of-00070.npy",
"data-00043-of-00070.npy",
"data-00044-of-00070.npy",
"data-00045-of-00070.npy",
"data-00046-of-00070.npy",
"data-00047-of-00070.npy",
"data-00048-of-00070.npy",
"data-00049-of-00070.npy",
"data-00050-of-00070.npy",
"data-00051-of-00070.npy",
"data-00052-of-00070.npy",
"data-00053-of-00070.npy",
"data-00054-of-00070.npy",
"data-00055-of-00070.npy",
"data-00056-of-00070.npy",
"data-00057-of-00070.npy",
"data-00058-of-00070.npy",
"data-00059-of-00070.npy",
"data-00060-of-00070.npy",
"data-00061-of-00070.npy",
"data-00062-of-00070.npy",
"data-00063-of-00070.npy",
"data-00064-of-00070.npy",
"data-00065-of-00070.npy",
"data-00066-of-00070.npy",
"data-00067-of-00070.npy",
"data-00068-of-00070.npy",
"data-00069-of-00070.npy"
],
"source_range": [
228,
563
],
"source_dataset": "allenai/dolma3_pool",
"source_config": "common_crawl-education_and_jobs-0003",
"created_at": "2026-08-17T22:56:53Z"
}

Xet Storage Details

Size:
2.55 kB
·
Xet hash:
cd4ba63f6a183f14340c36ff1d54cda555e64be7361b78cee57f048d7722906b

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