chatml-v1/_aggregate.json

{
  "bucket_prefix": "chatml-v1",
  "shards": 5,
  "docs": 1274433,
  "tokens": 608429952,
  "bytes": 1216859904,
  "per_source": {
    "A_distilled": {
      "docs": 98498,
      "tokens": 36786373
    },
    "B_ling30": {
      "docs": 13176,
      "tokens": 12039103
    },
    "C_ling30_simple": {
      "docs": 3172,
      "tokens": 1995944
    },
    "D_haiku": {
      "docs": 9998,
      "tokens": 3695534
    },
    "F_finetome": {
      "docs": 89280,
      "tokens": 36196963
    },
    "G_dcht": {
      "docs": 1001549,
      "tokens": 513537611
    },
    "H_contextqa": {
      "docs": 58760,
      "tokens": 4178424
    }
  },
  "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"
  ]
}