{
  "created_at_utc": "2026-05-10T20:47:18.183521Z",
  "dataset_id": "turkish-nlp-suite/BellaTurca",
  "subsets": [
    "AkademikDerlem",
    "OzenliDerlem",
    "temiz-OSCAR",
    "temiz-mC4"
  ],
  "split": "train",
  "text_column": "text",
  "vocab_size": 65536,
  "actual_vocab_size": 65536,
  "bpe_min_frequency": 3,
  "model_max_length": 262144,
  "target_total_est_tokens": 700000000,
  "target_per_subset_est_tokens": 175000000,
  "chars_per_est_token": 4.0,
  "cpu_threads": 1,
  "tokenizers_parallelism": "false",
  "row_batch_size": 2048,
  "max_chars_per_batch": 2000000,
  "max_text_chars": 512000,
  "stats": {
    "AkademikDerlem": {
      "rows": 269382,
      "chars": 700407485,
      "est_tokens": 175000688,
      "batches": 349,
      "exhausted": false,
      "started_at": 1778442491.6528769,
      "finished_at": 1778443380.1787434
    },
    "OzenliDerlem": {
      "rows": 247801,
      "chars": 700382884,
      "est_tokens": 175002937,
      "batches": 350,
      "exhausted": false,
      "started_at": 1778443381.5515542,
      "finished_at": 1778444260.174504
    },
    "temiz-OSCAR": {
      "rows": 339389,
      "chars": 700510176,
      "est_tokens": 175000312,
      "batches": 350,
      "exhausted": false,
      "started_at": 1778444261.4792535,
      "finished_at": 1778445104.4796338
    },
    "temiz-mC4": {
      "rows": 330530,
      "chars": 700479552,
      "est_tokens": 174996239,
      "batches": 350,
      "exhausted": false,
      "started_at": 1778445105.7765384,
      "finished_at": 1778445958.324916
    }
  },
  "special_tokens": [
    "<|pad|>",
    "<|bos|>",
    "<|eos|>",
    "<|unk|>",
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|answer|>",
    "<|end|>",
    "<think>",
    "</think>"
  ]
}