{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": null, "post_processor": null, "decoder": null, "model": { "type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "": 0, "\n": 1, "\r": 2, " ": 3, ",": 4, ".": 5, "a": 6, "b": 7, "c": 8, "d": 9, "e": 10, "f": 11, "g": 12, "h": 13, "i": 14, "k": 15, "l": 16, "m": 17, "n": 18, "o": 19, "p": 20, "q": 21, "r": 22, "s": 23, "t": 24, "u": 25, "w": 26, "y": 27, "e ": 28, "s ": 29, "it": 30, "th": 31, "n ": 32, "d ": 33, ", ": 34, "is ": 35, "al": 36, "an": 37, "ital": 38, "the ": 39, "ap": 40, "cap": 41, "capital": 42, "h ": 43, "of": 44, "or": 45, "and ": 46, "of ": 47, ". ": 48, "ar": 49, "in ": 50, "capital ": 51, "un": 52, "ur": 53, "ac": 54, "hi": 55, "ed ": 56, "st": 57, "\r\n": 58, "on": 59, "t ": 60, "the": 61, ", and ": 62, "capital of ": 63 }, "merges": [ [ "e", " " ], [ "s", " " ], [ "i", "t" ], [ "t", "h" ], [ "n", " " ], [ "d", " " ], [ ",", " " ], [ "i", "s " ], [ "a", "l" ], [ "a", "n" ], [ "it", "al" ], [ "th", "e " ], [ "a", "p" ], [ "c", "ap" ], [ "cap", "ital" ], [ "h", " " ], [ "o", "f" ], [ "o", "r" ], [ "an", "d " ], [ "of", " " ], [ ".", " " ], [ "a", "r" ], [ "i", "n " ], [ "capital", " " ], [ "u", "n" ], [ "u", "r" ], [ "a", "c" ], [ "h", "i" ], [ "e", "d " ], [ "s", "t" ], [ "\r", "\n" ], [ "o", "n" ], [ "t", " " ], [ "th", "e" ], [ ", ", "and " ], [ "capital ", "of " ] ] } }