{
  "builder_name": "jawiki-paragraphs",
  "citation": "",
  "config_name": "default",
  "dataset_size": 4417130987,
  "description": "\u66f8\u7c4d\u300e\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u5165\u9580\u300f\u3067\u4f7f\u7528\u3059\u308b Wikipedia \u6bb5\u843d\u306e\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u3059\u3002GitHub \u30ea\u30dd\u30b8\u30c8\u30ea singletongue/wikipedia-utils \u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u5229\u7528\u3057\u3066\u3044\u307e\u3059\u3002",
  "download_checksums": {
    "https://github.com/singletongue/wikipedia-utils/releases/download/2023-04-03/paragraphs-jawiki-20230403.json.gz": {
      "num_bytes": 1489512230,
      "checksum": null
    }
  },
  "download_size": 1489512230,
  "features": {
    "id": {
      "dtype": "string",
      "_type": "Value"
    },
    "pageid": {
      "dtype": "int64",
      "_type": "Value"
    },
    "revid": {
      "dtype": "int64",
      "_type": "Value"
    },
    "paragraph_index": {
      "dtype": "int64",
      "_type": "Value"
    },
    "title": {
      "dtype": "string",
      "_type": "Value"
    },
    "section": {
      "dtype": "string",
      "_type": "Value"
    },
    "text": {
      "dtype": "string",
      "_type": "Value"
    },
    "html_tag": {
      "dtype": "string",
      "_type": "Value"
    },
    "embeddings": {
      "feature": {
        "dtype": "float32",
        "_type": "Value"
      },
      "_type": "Sequence"
    }
  },
  "homepage": "https://github.com/singletongue/wikipedia-utils",
  "license": "\u672c\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u4f7f\u7528\u3057\u3066\u3044\u308b Wikipedia \u306e\u30b3\u30f3\u30c6\u30f3\u30c4\u306f\u3001\u30af\u30ea\u30a8\u30a4\u30c6\u30a3\u30d6\u30fb\u30b3\u30e2\u30f3\u30ba\u8868\u793a\u30fb\u7d99\u627f\u30e9\u30a4\u30bb\u30f3\u30b9 3.0 (CC BY-SA 3.0) \u304a\u3088\u3073 GNU \u81ea\u7531\u6587\u66f8\u30e9\u30a4\u30bb\u30f3\u30b9 (GFDL) \u306e\u4e0b\u306b\u914d\u5e03\u3055\u308c\u3066\u3044\u308b\u3082\u306e\u3067\u3059\u3002",
  "size_in_bytes": 5906643217,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 4417130987,
      "num_examples": 9668476,
      "shard_lengths": [
        984321,
        1031799,
        1101914,
        1132906,
        1123001,
        1143878,
        1138063,
        1139173,
        873421
      ],
      "dataset_name": "jawiki-paragraphs"
    }
  },
  "version": {
    "version_str": "1.0.0",
    "major": 1,
    "minor": 0,
    "patch": 0
  }
}