domofon/basic-prt / cosmo2 /_aggregate.json
domofon's picture
download
raw
1.52 kB
{
"dataset": "HuggingFaceTB/smollm-corpus",
"config": "cosmopedia-v2",
"split": "train",
"task": "cosmo2-b",
"bucket_prefix": "cosmo2",
"license": "Apache-2.0 (synthetic)",
"source_note": "CosmoPedia v2 files 21-26, continuation of cosmo2-a (non-overlapping)",
"ranges": [
{
"from_file": 21,
"to_file": 27
}
],
"shards": 31,
"rows": 2343758,
"tokens": 1688212214,
"bytes": 13524815120,
"files": [
"data-00090-of-00028.arrow",
"data-00091-of-00028.arrow",
"data-00092-of-00028.arrow",
"data-00093-of-00028.arrow",
"data-00094-of-00028.arrow",
"data-00095-of-00028.arrow",
"data-00096-of-00028.arrow",
"data-00097-of-00028.arrow",
"data-00098-of-00028.arrow",
"data-00099-of-00028.arrow",
"data-00100-of-00028.arrow",
"data-00101-of-00028.arrow",
"data-00102-of-00028.arrow",
"data-00103-of-00028.arrow",
"data-00104-of-00028.arrow",
"data-00105-of-00028.arrow",
"data-00106-of-00028.arrow",
"data-00107-of-00028.arrow",
"data-00108-of-00028.arrow",
"data-00109-of-00028.arrow",
"data-00110-of-00028.arrow",
"data-00111-of-00028.arrow",
"data-00112-of-00028.arrow",
"data-00113-of-00028.arrow",
"data-00114-of-00028.arrow",
"data-00115-of-00028.arrow",
"data-00116-of-00028.arrow",
"data-00117-of-00028.arrow",
"data-00118-of-00028.arrow",
"data-00119-of-00028.arrow",
"data-00120-of-00028.arrow"
],
"created": "2026-08-05T15:47:41.232443Z"
}

Xet Storage Details

Size:
1.52 kB
·
Xet hash:
def362dbf22da50782fcd757cc2f9c6255af95fe57776020062e9be3478d12a9

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