cosmo5b-03/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "cosmo5b-03",
  "corpus": "cosmo",
  "version": "5b",
  "shards": 9,
  "docs": 1505152,
  "tokens": 1084038125,
  "bytes": 2168076250,
  "files": [
    "data-00000-of-00009.npy",
    "data-00001-of-00009.npy",
    "data-00002-of-00009.npy",
    "data-00003-of-00009.npy",
    "data-00004-of-00009.npy",
    "data-00005-of-00009.npy",
    "data-00006-of-00009.npy",
    "data-00007-of-00009.npy",
    "data-00008-of-00009.npy"
  ],
  "source_range": [
    63,
    67
  ],
  "source_dataset": "HuggingFaceTB/smollm-corpus",
  "source_config": "cosmopedia-v2",
  "created_at": "2026-08-18T13:46:00Z"
}