dclm5b-t0/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "dclm5b-t0",
  "corpus": "dclm",
  "version": "5b",
  "shards": 2,
  "docs": 181114,
  "tokens": 221399039,
  "bytes": 442798078,
  "files": [
    "data-00000-of-00002.npy",
    "data-00001-of-00002.npy"
  ],
  "source_range": [
    22281,
    22283
  ],
  "source_dataset": "mlfoundations/dclm-baseline-1.0",
  "source_config": null,
  "created_at": "2026-08-18T15:56:29Z"
}