domofon/datasets / dolmino-dclm-r6 /_aggregate.json
domofon's picture
download
raw
2.03 kB
{
"engine": "tokforge",
"prefix": "dolmino-dclm-r6",
"corpus": "dolmino",
"version": "v1",
"shards": 54,
"docs": 5157712,
"tokens": 6750236731,
"bytes": 13500473462,
"files": [
"data-00000-of-00054.npy",
"data-00001-of-00054.npy",
"data-00002-of-00054.npy",
"data-00003-of-00054.npy",
"data-00004-of-00054.npy",
"data-00005-of-00054.npy",
"data-00006-of-00054.npy",
"data-00007-of-00054.npy",
"data-00008-of-00054.npy",
"data-00009-of-00054.npy",
"data-00010-of-00054.npy",
"data-00011-of-00054.npy",
"data-00012-of-00054.npy",
"data-00013-of-00054.npy",
"data-00014-of-00054.npy",
"data-00015-of-00054.npy",
"data-00016-of-00054.npy",
"data-00017-of-00054.npy",
"data-00018-of-00054.npy",
"data-00019-of-00054.npy",
"data-00020-of-00054.npy",
"data-00021-of-00054.npy",
"data-00022-of-00054.npy",
"data-00023-of-00054.npy",
"data-00024-of-00054.npy",
"data-00025-of-00054.npy",
"data-00026-of-00054.npy",
"data-00027-of-00054.npy",
"data-00028-of-00054.npy",
"data-00029-of-00054.npy",
"data-00030-of-00054.npy",
"data-00031-of-00054.npy",
"data-00032-of-00054.npy",
"data-00033-of-00054.npy",
"data-00034-of-00054.npy",
"data-00035-of-00054.npy",
"data-00036-of-00054.npy",
"data-00037-of-00054.npy",
"data-00038-of-00054.npy",
"data-00039-of-00054.npy",
"data-00040-of-00054.npy",
"data-00041-of-00054.npy",
"data-00042-of-00054.npy",
"data-00043-of-00054.npy",
"data-00044-of-00054.npy",
"data-00045-of-00054.npy",
"data-00046-of-00054.npy",
"data-00047-of-00054.npy",
"data-00048-of-00054.npy",
"data-00049-of-00054.npy",
"data-00050-of-00054.npy",
"data-00051-of-00054.npy",
"data-00052-of-00054.npy",
"data-00053-of-00054.npy"
],
"source_range": [
1846,
1870
],
"source_dataset": "allenai/dolmino-mix-1124",
"source_config": "dclm",
"created_at": "2026-08-31T02:14:42Z"
}

Xet Storage Details

Size:
2.03 kB
·
Xet hash:
71d8774fe502cbdb1fdbcfebe4ace466794f6cfe540f60baa1790a13d7d1bb5d

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