domofon/datasets / kaggle5b-00 /_aggregate.json
domofon's picture
download
raw
1.6 kB
{
"engine": "tokforge",
"prefix": "kaggle5b-00",
"corpus": "kaggle",
"version": "5b",
"shards": 40,
"docs": 7732532,
"tokens": 5000030082,
"bytes": 10000060164,
"files": [
"data-00000-of-00040.npy",
"data-00001-of-00040.npy",
"data-00002-of-00040.npy",
"data-00003-of-00040.npy",
"data-00004-of-00040.npy",
"data-00005-of-00040.npy",
"data-00006-of-00040.npy",
"data-00007-of-00040.npy",
"data-00008-of-00040.npy",
"data-00009-of-00040.npy",
"data-00010-of-00040.npy",
"data-00011-of-00040.npy",
"data-00012-of-00040.npy",
"data-00013-of-00040.npy",
"data-00014-of-00040.npy",
"data-00015-of-00040.npy",
"data-00016-of-00040.npy",
"data-00017-of-00040.npy",
"data-00018-of-00040.npy",
"data-00019-of-00040.npy",
"data-00020-of-00040.npy",
"data-00021-of-00040.npy",
"data-00022-of-00040.npy",
"data-00023-of-00040.npy",
"data-00024-of-00040.npy",
"data-00025-of-00040.npy",
"data-00026-of-00040.npy",
"data-00027-of-00040.npy",
"data-00028-of-00040.npy",
"data-00029-of-00040.npy",
"data-00030-of-00040.npy",
"data-00031-of-00040.npy",
"data-00032-of-00040.npy",
"data-00033-of-00040.npy",
"data-00034-of-00040.npy",
"data-00035-of-00040.npy",
"data-00036-of-00040.npy",
"data-00037-of-00040.npy",
"data-00038-of-00040.npy",
"data-00039-of-00040.npy"
],
"source_range": [
0,
73
],
"source_dataset": "HuggingFaceTB/issues-kaggle-notebooks",
"source_config": null,
"created_at": "2026-08-18T15:04:08Z"
}

Xet Storage Details

Size:
1.6 kB
·
Xet hash:
f51b35ad9d97263761acb9295023e09ce3be774a9492785a2b4184291959cf1d

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