tokforge-test-v8/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "tokforge-test-v8",
  "corpus": "cosmo2",
  "version": "v8",
  "shards": 15,
  "docs": 4196,
  "tokens": 3005929,
  "bytes": 6011858,
  "files": [
    "data-00000-of-00015.npy",
    "data-00001-of-00015.npy",
    "data-00002-of-00015.npy",
    "data-00003-of-00015.npy",
    "data-00004-of-00015.npy",
    "data-00005-of-00015.npy",
    "data-00006-of-00015.npy",
    "data-00007-of-00015.npy",
    "data-00008-of-00015.npy",
    "data-00009-of-00015.npy",
    "data-00010-of-00015.npy",
    "data-00011-of-00015.npy",
    "data-00012-of-00015.npy",
    "data-00013-of-00015.npy",
    "data-00014-of-00015.npy"
  ],
  "source_range": [
    0,
    1
  ],
  "source_dataset": "HuggingFaceTB/smollm-corpus",
  "source_config": "cosmopedia-v2",
  "created_at": "2026-08-15T22:11:05Z"
}