python-edu/_meta/data-00002-of-00038.json

{
  "shard": "data-00002-of-00038.arrow",
  "task": "python-edu-a",
  "dataset": "HuggingFaceTB/smollm-corpus",
  "config": "python-edu",
  "split": "train",
  "file_range": [
    0,
    1
  ],
  "rows": 86146,
  "tokens": 62000463,
  "bytes": 496706384,
  "sha256": "d4eb915f6450ea0e1f728d81187645cda2f5af4e5015c3241d0244fd07e07bc8",
  "schema": {
    "input_ids": "list<int32>",
    "labels": "list<int32>"
  },
  "eos_convention": "trailing <|endoftext|> id 0",
  "tokenizer": "HuggingFaceTB/SmolLM2-1.7B",
  "tokenizer_sha": "e6d44ded9564218b",
  "created": "2026-08-05T15:25:28.846841Z"
}