python-edu/_meta/data-00000-of-00038.json

{
  "shard": "data-00000-of-00038.arrow",
  "task": "python-edu-a",
  "dataset": "HuggingFaceTB/smollm-corpus",
  "config": "python-edu",
  "split": "train",
  "file_range": [
    0,
    1
  ],
  "rows": 86220,
  "tokens": 62000410,
  "bytes": 496706592,
  "sha256": "fae6d153974edcd70335ee36e98f935b8601f6e7487a01c91519fb89f6d3f05f",
  "schema": {
    "input_ids": "list<int32>",
    "labels": "list<int32>"
  },
  "eos_convention": "trailing <|endoftext|> id 0",
  "tokenizer": "HuggingFaceTB/SmolLM2-1.7B",
  "tokenizer_sha": "e6d44ded9564218b",
  "created": "2026-08-05T15:24:49.799296Z"
}