webinstr6b/_aggregate.json

{
  "engine": "tokforge",
  "prefix": "webinstr6b",
  "corpus": "webinstruct",
  "version": "v6",
  "shards": 5,
  "docs": 1796303,
  "tokens": 510487802,
  "bytes": 1020975604,
  "files": [
    "data-00000-of-00005.npy",
    "data-00001-of-00005.npy",
    "data-00002-of-00005.npy",
    "data-00003-of-00005.npy",
    "data-00004-of-00005.npy"
  ],
  "source_range": [
    0,
    10
  ],
  "source_dataset": "TIGER-Lab/WebInstructSub",
  "source_config": null,
  "created_at": "2026-08-19T16:42:24Z"
}