diff --git "a/tokenizer.json" "b/tokenizer.json"
new file mode 100644--- /dev/null
+++ "b/tokenizer.json"
@@ -0,0 +1,59451 @@
+{
+ "version": "1.0",
+ "truncation": null,
+ "padding": null,
+ "added_tokens": [
+ {
+ "id": 0,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 1,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 2,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 3,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 4,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 5,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 6,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ },
+ {
+ "id": 7,
+ "content": "",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": false,
+ "special": true
+ }
+ ],
+ "normalizer": null,
+ "pre_tokenizer": {
+ "type": "Whitespace"
+ },
+ "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,
+ "": 1,
+ "": 2,
+ "": 3,
+ "": 4,
+ "": 5,
+ "": 6,
+ "": 7,
+ "!": 8,
+ "\"": 9,
+ "#": 10,
+ "$": 11,
+ "%": 12,
+ "&": 13,
+ "'": 14,
+ "(": 15,
+ ")": 16,
+ "*": 17,
+ "+": 18,
+ ",": 19,
+ "-": 20,
+ ".": 21,
+ "/": 22,
+ "0": 23,
+ "1": 24,
+ "2": 25,
+ "3": 26,
+ "4": 27,
+ "5": 28,
+ "6": 29,
+ "7": 30,
+ "8": 31,
+ "9": 32,
+ ":": 33,
+ ";": 34,
+ "<": 35,
+ "=": 36,
+ ">": 37,
+ "?": 38,
+ "A": 39,
+ "B": 40,
+ "C": 41,
+ "D": 42,
+ "E": 43,
+ "F": 44,
+ "G": 45,
+ "H": 46,
+ "I": 47,
+ "J": 48,
+ "K": 49,
+ "L": 50,
+ "M": 51,
+ "N": 52,
+ "O": 53,
+ "P": 54,
+ "Q": 55,
+ "R": 56,
+ "S": 57,
+ "T": 58,
+ "U": 59,
+ "V": 60,
+ "W": 61,
+ "X": 62,
+ "Y": 63,
+ "Z": 64,
+ "[": 65,
+ "\\": 66,
+ "]": 67,
+ "_": 68,
+ "a": 69,
+ "b": 70,
+ "c": 71,
+ "d": 72,
+ "e": 73,
+ "f": 74,
+ "g": 75,
+ "h": 76,
+ "i": 77,
+ "j": 78,
+ "k": 79,
+ "l": 80,
+ "m": 81,
+ "n": 82,
+ "o": 83,
+ "p": 84,
+ "q": 85,
+ "r": 86,
+ "s": 87,
+ "t": 88,
+ "u": 89,
+ "v": 90,
+ "w": 91,
+ "x": 92,
+ "y": 93,
+ "z": 94,
+ "{": 95,
+ "|": 96,
+ "}": 97,
+ "~": 98,
+ "ª": 99,
+ "°": 100,
+ "³": 101,
+ "º": 102,
+ "À": 103,
+ "Á": 104,
+ "Ã": 105,
+ "Ç": 106,
+ "É": 107,
+ "Í": 108,
+ "Ó": 109,
+ "×": 110,
+ "ß": 111,
+ "à": 112,
+ "á": 113,
+ "â": 114,
+ "ã": 115,
+ "ç": 116,
+ "è": 117,
+ "é": 118,
+ "ê": 119,
+ "ì": 120,
+ "í": 121,
+ "ñ": 122,
+ "ò": 123,
+ "ó": 124,
+ "ô": 125,
+ "õ": 126,
+ "ö": 127,
+ "ø": 128,
+ "ú": 129,
+ "ü": 130,
+ "ă": 131,
+ "ć": 132,
+ "Č": 133,
+ "č": 134,
+ "ě": 135,
+ "ī": 136,
+ "ō": 137,
+ "ś": 138,
+ "ş": 139,
+ "š": 140,
+ "ž": 141,
+ "Φ": 142,
+ "έ": 143,
+ "α": 144,
+ "θ": 145,
+ "ν": 146,
+ "ω": 147,
+ "": 148,
+ "–": 149,
+ "—": 150,
+ "’": 151,
+ "“": 152,
+ "”": 153,
+ "∞": 154,
+ "≈": 155,
+ "✅": 156,
+ "❌": 157,
+ "岁": 158,
+ "星": 159,
+ "木": 160,
+ "歲": 161,
+ "te": 162,
+ "ER": 163,
+ "de": 164,
+ "ão": 165,
+ "is": 166,
+ "ra": 167,
+ "ca": 168,
+ "