dclm5b-t1/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "dclm5b-t1",
  "corpus": "dclm",
  "version": "5b",
  "shards": 3,
  "docs": 232188,
  "tokens": 326670945,
  "bytes": 653341890,
  "files": [
    "data-00000-of-00003.npy",
    "data-00001-of-00003.npy",
    "data-00002-of-00003.npy"
  ],
  "source_range": [
    16526,
    16528
  ],
  "source_dataset": "mlfoundations/dclm-baseline-1.0",
  "source_config": null,
  "created_at": "2026-08-18T15:59:16Z"
}