Add tokenizer files
Browse files- tokenizer.json +4 -61
tokenizer.json
CHANGED
|
@@ -119,67 +119,10 @@
|
|
| 119 |
"14": 45,
|
| 120 |
"15": 46,
|
| 121 |
"16": 47,
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"21": 52,
|
| 127 |
-
"22": 53,
|
| 128 |
-
"23": 54,
|
| 129 |
-
"24": 55,
|
| 130 |
-
"25": 56,
|
| 131 |
-
"26": 57,
|
| 132 |
-
"27": 58,
|
| 133 |
-
"28": 59,
|
| 134 |
-
"29": 60,
|
| 135 |
-
"30": 61,
|
| 136 |
-
"31": 62,
|
| 137 |
-
"32": 63,
|
| 138 |
-
"33": 64,
|
| 139 |
-
"34": 65,
|
| 140 |
-
"35": 66,
|
| 141 |
-
"36": 67,
|
| 142 |
-
"37": 68,
|
| 143 |
-
"38": 69,
|
| 144 |
-
"39": 70,
|
| 145 |
-
"40": 71,
|
| 146 |
-
"41": 72,
|
| 147 |
-
"42": 73,
|
| 148 |
-
"43": 74,
|
| 149 |
-
"44": 75,
|
| 150 |
-
"45": 76,
|
| 151 |
-
"46": 77,
|
| 152 |
-
"47": 78,
|
| 153 |
-
"48": 79,
|
| 154 |
-
"49": 80,
|
| 155 |
-
"50": 81,
|
| 156 |
-
"51": 82,
|
| 157 |
-
"52": 83,
|
| 158 |
-
"53": 84,
|
| 159 |
-
"54": 85,
|
| 160 |
-
"55": 86,
|
| 161 |
-
"56": 87,
|
| 162 |
-
"57": 88,
|
| 163 |
-
"58": 89,
|
| 164 |
-
"59": 90,
|
| 165 |
-
"60": 91,
|
| 166 |
-
"61": 92,
|
| 167 |
-
"62": 93,
|
| 168 |
-
"63": 94,
|
| 169 |
-
"64": 95,
|
| 170 |
-
"65": 96,
|
| 171 |
-
"66": 97,
|
| 172 |
-
"67": 98,
|
| 173 |
-
"68": 99,
|
| 174 |
-
"69": 100,
|
| 175 |
-
"70": 101,
|
| 176 |
-
"71": 102,
|
| 177 |
-
"72": 103,
|
| 178 |
-
"73": 104,
|
| 179 |
-
"74": 105,
|
| 180 |
-
"75": 106,
|
| 181 |
-
"|": 107,
|
| 182 |
-
"?": 108
|
| 183 |
},
|
| 184 |
"unk_token": "[UNK]"
|
| 185 |
}
|
|
|
|
| 119 |
"14": 45,
|
| 120 |
"15": 46,
|
| 121 |
"16": 47,
|
| 122 |
+
"|": 48,
|
| 123 |
+
"?": 49,
|
| 124 |
+
"(": 50,
|
| 125 |
+
")": 51
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
},
|
| 127 |
"unk_token": "[UNK]"
|
| 128 |
}
|