webinstr6b-t1/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "webinstr6b-t1",
  "corpus": "webinstruct",
  "version": "v6",
  "shards": 6,
  "docs": 2430617,
  "tokens": 750002235,
  "bytes": 1500004470,
  "files": [
    "data-00000-of-00006.npy",
    "data-00001-of-00006.npy",
    "data-00002-of-00006.npy",
    "data-00003-of-00006.npy",
    "data-00004-of-00006.npy",
    "data-00005-of-00006.npy"
  ],
  "source_range": [
    0,
    6
  ],
  "source_dataset": "TIGER-Lab/WebInstructFull",
  "source_config": null,
  "created_at": "2026-08-19T20:55:04Z"
}