Update tokenizer.json
Browse files- tokenizer.json +96 -95
tokenizer.json
CHANGED
|
@@ -27,101 +27,102 @@
|
|
| 27 |
"byte_fallback": false,
|
| 28 |
"vocab": {
|
| 29 |
"[UNK]": 0,
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
| 110 |
-
"
|
| 111 |
-
"
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
|
|
|
| 125 |
},
|
| 126 |
"merges": []
|
| 127 |
}
|
|
|
|
| 27 |
"byte_fallback": false,
|
| 28 |
"vocab": {
|
| 29 |
"[UNK]": 0,
|
| 30 |
+
"[MASK]": 1,
|
| 31 |
+
"0": 2,
|
| 32 |
+
"1": 3,
|
| 33 |
+
"2": 4,
|
| 34 |
+
"3": 5,
|
| 35 |
+
"4": 6,
|
| 36 |
+
"5": 7,
|
| 37 |
+
"6": 8,
|
| 38 |
+
"7": 9,
|
| 39 |
+
"8": 10,
|
| 40 |
+
"9": 11,
|
| 41 |
+
"a": 12,
|
| 42 |
+
"b": 13,
|
| 43 |
+
"c": 14,
|
| 44 |
+
"d": 15,
|
| 45 |
+
"e": 16,
|
| 46 |
+
"f": 17,
|
| 47 |
+
"g": 18,
|
| 48 |
+
"h": 19,
|
| 49 |
+
"i": 20,
|
| 50 |
+
"j": 21,
|
| 51 |
+
"k": 22,
|
| 52 |
+
"l": 23,
|
| 53 |
+
"m": 24,
|
| 54 |
+
"n": 25,
|
| 55 |
+
"o": 26,
|
| 56 |
+
"p": 27,
|
| 57 |
+
"q": 28,
|
| 58 |
+
"r": 29,
|
| 59 |
+
"s": 30,
|
| 60 |
+
"t": 31,
|
| 61 |
+
"u": 32,
|
| 62 |
+
"v": 33,
|
| 63 |
+
"w": 34,
|
| 64 |
+
"x": 35,
|
| 65 |
+
"y": 36,
|
| 66 |
+
"z": 37,
|
| 67 |
+
"A": 38,
|
| 68 |
+
"B": 39,
|
| 69 |
+
"C": 40,
|
| 70 |
+
"D": 41,
|
| 71 |
+
"E": 42,
|
| 72 |
+
"F": 43,
|
| 73 |
+
"G": 44,
|
| 74 |
+
"H": 45,
|
| 75 |
+
"I": 46,
|
| 76 |
+
"J": 47,
|
| 77 |
+
"K": 48,
|
| 78 |
+
"L": 49,
|
| 79 |
+
"M": 50,
|
| 80 |
+
"N": 51,
|
| 81 |
+
"O": 52,
|
| 82 |
+
"P": 53,
|
| 83 |
+
"Q": 54,
|
| 84 |
+
"R": 55,
|
| 85 |
+
"S": 56,
|
| 86 |
+
"T": 57,
|
| 87 |
+
"U": 58,
|
| 88 |
+
"V": 59,
|
| 89 |
+
"W": 60,
|
| 90 |
+
"X": 61,
|
| 91 |
+
"Y": 62,
|
| 92 |
+
"Z": 63,
|
| 93 |
+
"!": 64,
|
| 94 |
+
"\"": 65,
|
| 95 |
+
"#": 66,
|
| 96 |
+
"$": 67,
|
| 97 |
+
"%": 68,
|
| 98 |
+
"&": 69,
|
| 99 |
+
"'": 70,
|
| 100 |
+
"(": 71,
|
| 101 |
+
")": 72,
|
| 102 |
+
"*": 73,
|
| 103 |
+
"+": 74,
|
| 104 |
+
",": 75,
|
| 105 |
+
"-": 76,
|
| 106 |
+
".": 77,
|
| 107 |
+
"/": 78,
|
| 108 |
+
":": 79,
|
| 109 |
+
";": 80,
|
| 110 |
+
"<": 81,
|
| 111 |
+
"=": 82,
|
| 112 |
+
">": 83,
|
| 113 |
+
"?": 84,
|
| 114 |
+
"@": 85,
|
| 115 |
+
"[": 86,
|
| 116 |
+
"\\": 87,
|
| 117 |
+
"]": 88,
|
| 118 |
+
"^": 89,
|
| 119 |
+
"_": 90,
|
| 120 |
+
"`": 91,
|
| 121 |
+
"{": 92,
|
| 122 |
+
"|": 93,
|
| 123 |
+
"}": 94,
|
| 124 |
+
"~": 95,
|
| 125 |
+
" ": 96
|
| 126 |
},
|
| 127 |
"merges": []
|
| 128 |
}
|