python-edu/_meta/data-00001-of-00038.json

{
  "shard": "data-00001-of-00038.arrow",
  "task": "python-edu-a",
  "dataset": "HuggingFaceTB/smollm-corpus",
  "config": "python-edu",
  "split": "train",
  "file_range": [
    0,
    1
  ],
  "rows": 86084,
  "tokens": 62000011,
  "bytes": 496702288,
  "sha256": "8cde8ba6be5f7408066f1056660cd090705dd6f0bd7c5484f826155292695c31",
  "schema": {
    "input_ids": "list<int32>",
    "labels": "list<int32>"
  },
  "eos_convention": "trailing <|endoftext|> id 0",
  "tokenizer": "HuggingFaceTB/SmolLM2-1.7B",
  "tokenizer_sha": "e6d44ded9564218b",
  "created": "2026-08-05T15:25:09.484668Z"
}