domofon/datasets / dolma3-cc-v1 /_aggregate.json
domofon's picture
download
raw
1.43 kB
{
"engine": "tokforge",
"prefix": "dolma3-cc-v1",
"corpus": "dolma3",
"version": "v1",
"shards": 34,
"docs": 10298190,
"tokens": 4142408617,
"bytes": 8284817234,
"files": [
"data-00000-of-00034.npy",
"data-00001-of-00034.npy",
"data-00002-of-00034.npy",
"data-00003-of-00034.npy",
"data-00004-of-00034.npy",
"data-00005-of-00034.npy",
"data-00006-of-00034.npy",
"data-00007-of-00034.npy",
"data-00008-of-00034.npy",
"data-00009-of-00034.npy",
"data-00010-of-00034.npy",
"data-00011-of-00034.npy",
"data-00012-of-00034.npy",
"data-00013-of-00034.npy",
"data-00014-of-00034.npy",
"data-00015-of-00034.npy",
"data-00016-of-00034.npy",
"data-00017-of-00034.npy",
"data-00018-of-00034.npy",
"data-00019-of-00034.npy",
"data-00020-of-00034.npy",
"data-00021-of-00034.npy",
"data-00022-of-00034.npy",
"data-00023-of-00034.npy",
"data-00024-of-00034.npy",
"data-00025-of-00034.npy",
"data-00026-of-00034.npy",
"data-00027-of-00034.npy",
"data-00028-of-00034.npy",
"data-00029-of-00034.npy",
"data-00030-of-00034.npy",
"data-00031-of-00034.npy",
"data-00032-of-00034.npy",
"data-00033-of-00034.npy"
],
"source_range": [
2,
160
],
"source_dataset": "allenai/dolma3_pool",
"source_config": "common_crawl-education_and_jobs-0003",
"created_at": "2026-08-17T19:57:55Z"
}

Xet Storage Details

Size:
1.43 kB
·
Xet hash:
f965c1db9a4c17eaaf4055d80c03a0e054be2d844c0ec441e6896300898a91e4

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