v2/tokenizer.json

{
  "the": 0,
  "capital": 1,
  "of": 2,
  "united": 3,
  "state": 4,
  "is": 5,
  "not": 6,
  "london": 7,
  "france": 8,
  "paris": 9,
  "and": 10,
  "berlin": 11,
  "germany": 12,
  "rome": 13,
  "in": 14,
  "italy": 15,
  "madrid": 16,
  "spain": 17,
  "lisbon": 18,
  "portugal": 19,
  "kingdom": 20,
  "washington": 21,
  "although": 22,
  "these": 23,
  "place": 24,
  "are": 25,
  "often": 26,
  "mention": 27,
  "together": 28,
  "each": 29,
  "country": 30,
  "has": 31,
  "its": 32,
  "own": 33,
  "identity": 34,
  "any": 35,
  "european": 36,
  "city": 37,
  "remain": 38,
  "important": 39,
  "with": 40,
  "a": 41,
  "rich": 42,
  "history": 43,
  "culture": 44,
  "europe": 45,
  "made": 46,
  "many": 47,
  "unique": 48,
  "world": 49,
  "while": 50,
  "known": 51,
  "for": 52,
  "art": 53,
  "fashion": 54,
  "famous": 55,
  "they": 56,
  "ed": 57,
  "s": 58,
  ".": 59,
  ",": 60,
  " ": 61,
  "<unk>": 62,
  "<pad>": 63
}