tokforge-test-v10/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "tokforge-test-v10",
  "corpus": "cosmo2",
  "version": "v10",
  "shards": 26,
  "docs": 7295,
  "tokens": 5211657,
  "bytes": 10423314,
  "files": [
    "data-00000-of-00025.npy",
    "data-00001-of-00025.npy",
    "data-00002-of-00025.npy",
    "data-00003-of-00025.npy",
    "data-00004-of-00025.npy",
    "data-00005-of-00025.npy",
    "data-00006-of-00025.npy",
    "data-00007-of-00025.npy",
    "data-00008-of-00025.npy",
    "data-00009-of-00025.npy",
    "data-00010-of-00025.npy",
    "data-00011-of-00025.npy",
    "data-00012-of-00025.npy",
    "data-00013-of-00025.npy",
    "data-00014-of-00025.npy",
    "data-00015-of-00025.npy",
    "data-00016-of-00025.npy",
    "data-00017-of-00025.npy",
    "data-00018-of-00025.npy",
    "data-00019-of-00025.npy",
    "data-00020-of-00025.npy",
    "data-00021-of-00025.npy",
    "data-00022-of-00025.npy",
    "data-00023-of-00025.npy",
    "data-00024-of-00025.npy",
    "data-00025-of-00026.npy"
  ],
  "source_range": [
    2,
    3
  ],
  "source_dataset": "HuggingFaceTB/smollm-corpus",
  "source_config": "cosmopedia-v2",
  "created_at": "2026-08-15T22:18:57Z"
}