{
  "dataset": "HuggingFaceTB/smollm-corpus",
  "config": "python-edu",
  "split": "train",
  "task": "python-edu-a",
  "bucket_prefix": "python-edu",
  "license": "Apache-2.0",
  "source_note": "Python-Edu subset of smollm-corpus, first parquet file",
  "ranges": [
    {
      "from_file": 0,
      "to_file": 1
    }
  ],
  "shards": 5,
  "rows": 376289,
  "tokens": 270931486,
  "bytes": 2170521184,
  "files": [
    "data-00000-of-00038.arrow",
    "data-00001-of-00038.arrow",
    "data-00002-of-00038.arrow",
    "data-00003-of-00038.arrow",
    "data-00004-of-00038.arrow"
  ],
  "created": "2026-08-05T15:25:58.929259Z"
}