Add tokenizer files
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +711 -0
- tokenizer_config.json +53 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[BOS]",
|
| 3 |
+
"eos_token": "[EOS]",
|
| 4 |
+
"mask_token": "_",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,711 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "_",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[UNK]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[BOS]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[EOS]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "Sequence",
|
| 54 |
+
"normalizers": [
|
| 55 |
+
{
|
| 56 |
+
"type": "NFD"
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"type": "StripAccents"
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"type": "Lowercase"
|
| 63 |
+
}
|
| 64 |
+
]
|
| 65 |
+
},
|
| 66 |
+
"pre_tokenizer": {
|
| 67 |
+
"type": "Whitespace"
|
| 68 |
+
},
|
| 69 |
+
"post_processor": null,
|
| 70 |
+
"decoder": null,
|
| 71 |
+
"model": {
|
| 72 |
+
"type": "WordLevel",
|
| 73 |
+
"vocab": {
|
| 74 |
+
"_": 0,
|
| 75 |
+
"[PAD]": 1,
|
| 76 |
+
"[UNK]": 2,
|
| 77 |
+
"[BOS]": 3,
|
| 78 |
+
"[EOS]": 4,
|
| 79 |
+
"a": 5,
|
| 80 |
+
"b": 6,
|
| 81 |
+
"c": 7,
|
| 82 |
+
"d": 8,
|
| 83 |
+
"e": 9,
|
| 84 |
+
"f": 10,
|
| 85 |
+
"g": 11,
|
| 86 |
+
"h": 12,
|
| 87 |
+
"i": 13,
|
| 88 |
+
"j": 14,
|
| 89 |
+
"k": 15,
|
| 90 |
+
"l": 16,
|
| 91 |
+
"m": 17,
|
| 92 |
+
"n": 18,
|
| 93 |
+
"o": 19,
|
| 94 |
+
"p": 20,
|
| 95 |
+
"q": 21,
|
| 96 |
+
"r": 22,
|
| 97 |
+
"s": 23,
|
| 98 |
+
"t": 24,
|
| 99 |
+
"u": 25,
|
| 100 |
+
"v": 26,
|
| 101 |
+
"w": 27,
|
| 102 |
+
"x": 28,
|
| 103 |
+
"y": 29,
|
| 104 |
+
"z": 30,
|
| 105 |
+
"0": 31,
|
| 106 |
+
"1": 32,
|
| 107 |
+
"2": 33,
|
| 108 |
+
"3": 34,
|
| 109 |
+
"4": 35,
|
| 110 |
+
"5": 36,
|
| 111 |
+
"6": 37,
|
| 112 |
+
"7": 38,
|
| 113 |
+
"8": 39,
|
| 114 |
+
"9": 40,
|
| 115 |
+
"10": 41,
|
| 116 |
+
"11": 42,
|
| 117 |
+
"12": 43,
|
| 118 |
+
"13": 44,
|
| 119 |
+
"14": 45,
|
| 120 |
+
"15": 46,
|
| 121 |
+
"16": 47,
|
| 122 |
+
"17": 48,
|
| 123 |
+
"18": 49,
|
| 124 |
+
"19": 50,
|
| 125 |
+
"20": 51,
|
| 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 |
+
"76": 107,
|
| 182 |
+
"77": 108,
|
| 183 |
+
"78": 109,
|
| 184 |
+
"79": 110,
|
| 185 |
+
"80": 111,
|
| 186 |
+
"81": 112,
|
| 187 |
+
"82": 113,
|
| 188 |
+
"83": 114,
|
| 189 |
+
"84": 115,
|
| 190 |
+
"85": 116,
|
| 191 |
+
"86": 117,
|
| 192 |
+
"87": 118,
|
| 193 |
+
"88": 119,
|
| 194 |
+
"89": 120,
|
| 195 |
+
"90": 121,
|
| 196 |
+
"91": 122,
|
| 197 |
+
"92": 123,
|
| 198 |
+
"93": 124,
|
| 199 |
+
"94": 125,
|
| 200 |
+
"95": 126,
|
| 201 |
+
"96": 127,
|
| 202 |
+
"97": 128,
|
| 203 |
+
"98": 129,
|
| 204 |
+
"99": 130,
|
| 205 |
+
"100": 131,
|
| 206 |
+
"101": 132,
|
| 207 |
+
"102": 133,
|
| 208 |
+
"103": 134,
|
| 209 |
+
"104": 135,
|
| 210 |
+
"105": 136,
|
| 211 |
+
"106": 137,
|
| 212 |
+
"107": 138,
|
| 213 |
+
"108": 139,
|
| 214 |
+
"109": 140,
|
| 215 |
+
"110": 141,
|
| 216 |
+
"111": 142,
|
| 217 |
+
"112": 143,
|
| 218 |
+
"113": 144,
|
| 219 |
+
"114": 145,
|
| 220 |
+
"115": 146,
|
| 221 |
+
"116": 147,
|
| 222 |
+
"117": 148,
|
| 223 |
+
"118": 149,
|
| 224 |
+
"119": 150,
|
| 225 |
+
"120": 151,
|
| 226 |
+
"121": 152,
|
| 227 |
+
"122": 153,
|
| 228 |
+
"123": 154,
|
| 229 |
+
"124": 155,
|
| 230 |
+
"125": 156,
|
| 231 |
+
"126": 157,
|
| 232 |
+
"127": 158,
|
| 233 |
+
"128": 159,
|
| 234 |
+
"129": 160,
|
| 235 |
+
"130": 161,
|
| 236 |
+
"131": 162,
|
| 237 |
+
"132": 163,
|
| 238 |
+
"133": 164,
|
| 239 |
+
"134": 165,
|
| 240 |
+
"135": 166,
|
| 241 |
+
"136": 167,
|
| 242 |
+
"137": 168,
|
| 243 |
+
"138": 169,
|
| 244 |
+
"139": 170,
|
| 245 |
+
"140": 171,
|
| 246 |
+
"141": 172,
|
| 247 |
+
"142": 173,
|
| 248 |
+
"143": 174,
|
| 249 |
+
"144": 175,
|
| 250 |
+
"145": 176,
|
| 251 |
+
"146": 177,
|
| 252 |
+
"147": 178,
|
| 253 |
+
"148": 179,
|
| 254 |
+
"149": 180,
|
| 255 |
+
"150": 181,
|
| 256 |
+
"151": 182,
|
| 257 |
+
"152": 183,
|
| 258 |
+
"153": 184,
|
| 259 |
+
"154": 185,
|
| 260 |
+
"155": 186,
|
| 261 |
+
"156": 187,
|
| 262 |
+
"157": 188,
|
| 263 |
+
"158": 189,
|
| 264 |
+
"159": 190,
|
| 265 |
+
"160": 191,
|
| 266 |
+
"161": 192,
|
| 267 |
+
"162": 193,
|
| 268 |
+
"163": 194,
|
| 269 |
+
"164": 195,
|
| 270 |
+
"165": 196,
|
| 271 |
+
"166": 197,
|
| 272 |
+
"167": 198,
|
| 273 |
+
"168": 199,
|
| 274 |
+
"169": 200,
|
| 275 |
+
"170": 201,
|
| 276 |
+
"171": 202,
|
| 277 |
+
"172": 203,
|
| 278 |
+
"173": 204,
|
| 279 |
+
"174": 205,
|
| 280 |
+
"175": 206,
|
| 281 |
+
"176": 207,
|
| 282 |
+
"177": 208,
|
| 283 |
+
"178": 209,
|
| 284 |
+
"179": 210,
|
| 285 |
+
"180": 211,
|
| 286 |
+
"181": 212,
|
| 287 |
+
"182": 213,
|
| 288 |
+
"183": 214,
|
| 289 |
+
"184": 215,
|
| 290 |
+
"185": 216,
|
| 291 |
+
"186": 217,
|
| 292 |
+
"187": 218,
|
| 293 |
+
"188": 219,
|
| 294 |
+
"189": 220,
|
| 295 |
+
"190": 221,
|
| 296 |
+
"191": 222,
|
| 297 |
+
"192": 223,
|
| 298 |
+
"193": 224,
|
| 299 |
+
"194": 225,
|
| 300 |
+
"195": 226,
|
| 301 |
+
"196": 227,
|
| 302 |
+
"197": 228,
|
| 303 |
+
"198": 229,
|
| 304 |
+
"199": 230,
|
| 305 |
+
"200": 231,
|
| 306 |
+
"201": 232,
|
| 307 |
+
"202": 233,
|
| 308 |
+
"203": 234,
|
| 309 |
+
"204": 235,
|
| 310 |
+
"205": 236,
|
| 311 |
+
"206": 237,
|
| 312 |
+
"207": 238,
|
| 313 |
+
"208": 239,
|
| 314 |
+
"209": 240,
|
| 315 |
+
"210": 241,
|
| 316 |
+
"211": 242,
|
| 317 |
+
"212": 243,
|
| 318 |
+
"213": 244,
|
| 319 |
+
"214": 245,
|
| 320 |
+
"215": 246,
|
| 321 |
+
"216": 247,
|
| 322 |
+
"217": 248,
|
| 323 |
+
"218": 249,
|
| 324 |
+
"219": 250,
|
| 325 |
+
"220": 251,
|
| 326 |
+
"221": 252,
|
| 327 |
+
"222": 253,
|
| 328 |
+
"223": 254,
|
| 329 |
+
"224": 255,
|
| 330 |
+
"225": 256,
|
| 331 |
+
"226": 257,
|
| 332 |
+
"227": 258,
|
| 333 |
+
"228": 259,
|
| 334 |
+
"229": 260,
|
| 335 |
+
"230": 261,
|
| 336 |
+
"231": 262,
|
| 337 |
+
"232": 263,
|
| 338 |
+
"233": 264,
|
| 339 |
+
"234": 265,
|
| 340 |
+
"235": 266,
|
| 341 |
+
"236": 267,
|
| 342 |
+
"237": 268,
|
| 343 |
+
"238": 269,
|
| 344 |
+
"239": 270,
|
| 345 |
+
"240": 271,
|
| 346 |
+
"241": 272,
|
| 347 |
+
"242": 273,
|
| 348 |
+
"243": 274,
|
| 349 |
+
"244": 275,
|
| 350 |
+
"245": 276,
|
| 351 |
+
"246": 277,
|
| 352 |
+
"247": 278,
|
| 353 |
+
"248": 279,
|
| 354 |
+
"249": 280,
|
| 355 |
+
"250": 281,
|
| 356 |
+
"251": 282,
|
| 357 |
+
"252": 283,
|
| 358 |
+
"253": 284,
|
| 359 |
+
"254": 285,
|
| 360 |
+
"255": 286,
|
| 361 |
+
"256": 287,
|
| 362 |
+
"257": 288,
|
| 363 |
+
"258": 289,
|
| 364 |
+
"259": 290,
|
| 365 |
+
"260": 291,
|
| 366 |
+
"261": 292,
|
| 367 |
+
"262": 293,
|
| 368 |
+
"263": 294,
|
| 369 |
+
"264": 295,
|
| 370 |
+
"265": 296,
|
| 371 |
+
"266": 297,
|
| 372 |
+
"267": 298,
|
| 373 |
+
"268": 299,
|
| 374 |
+
"269": 300,
|
| 375 |
+
"270": 301,
|
| 376 |
+
"271": 302,
|
| 377 |
+
"272": 303,
|
| 378 |
+
"273": 304,
|
| 379 |
+
"274": 305,
|
| 380 |
+
"275": 306,
|
| 381 |
+
"276": 307,
|
| 382 |
+
"277": 308,
|
| 383 |
+
"278": 309,
|
| 384 |
+
"279": 310,
|
| 385 |
+
"280": 311,
|
| 386 |
+
"281": 312,
|
| 387 |
+
"282": 313,
|
| 388 |
+
"283": 314,
|
| 389 |
+
"284": 315,
|
| 390 |
+
"285": 316,
|
| 391 |
+
"286": 317,
|
| 392 |
+
"287": 318,
|
| 393 |
+
"288": 319,
|
| 394 |
+
"289": 320,
|
| 395 |
+
"290": 321,
|
| 396 |
+
"291": 322,
|
| 397 |
+
"292": 323,
|
| 398 |
+
"293": 324,
|
| 399 |
+
"294": 325,
|
| 400 |
+
"295": 326,
|
| 401 |
+
"296": 327,
|
| 402 |
+
"297": 328,
|
| 403 |
+
"298": 329,
|
| 404 |
+
"299": 330,
|
| 405 |
+
"300": 331,
|
| 406 |
+
"301": 332,
|
| 407 |
+
"302": 333,
|
| 408 |
+
"303": 334,
|
| 409 |
+
"304": 335,
|
| 410 |
+
"305": 336,
|
| 411 |
+
"306": 337,
|
| 412 |
+
"307": 338,
|
| 413 |
+
"308": 339,
|
| 414 |
+
"309": 340,
|
| 415 |
+
"310": 341,
|
| 416 |
+
"311": 342,
|
| 417 |
+
"312": 343,
|
| 418 |
+
"313": 344,
|
| 419 |
+
"314": 345,
|
| 420 |
+
"315": 346,
|
| 421 |
+
"316": 347,
|
| 422 |
+
"317": 348,
|
| 423 |
+
"318": 349,
|
| 424 |
+
"319": 350,
|
| 425 |
+
"320": 351,
|
| 426 |
+
"321": 352,
|
| 427 |
+
"322": 353,
|
| 428 |
+
"323": 354,
|
| 429 |
+
"324": 355,
|
| 430 |
+
"325": 356,
|
| 431 |
+
"326": 357,
|
| 432 |
+
"327": 358,
|
| 433 |
+
"328": 359,
|
| 434 |
+
"329": 360,
|
| 435 |
+
"330": 361,
|
| 436 |
+
"331": 362,
|
| 437 |
+
"332": 363,
|
| 438 |
+
"333": 364,
|
| 439 |
+
"334": 365,
|
| 440 |
+
"335": 366,
|
| 441 |
+
"336": 367,
|
| 442 |
+
"337": 368,
|
| 443 |
+
"338": 369,
|
| 444 |
+
"339": 370,
|
| 445 |
+
"340": 371,
|
| 446 |
+
"341": 372,
|
| 447 |
+
"342": 373,
|
| 448 |
+
"343": 374,
|
| 449 |
+
"344": 375,
|
| 450 |
+
"345": 376,
|
| 451 |
+
"346": 377,
|
| 452 |
+
"347": 378,
|
| 453 |
+
"348": 379,
|
| 454 |
+
"349": 380,
|
| 455 |
+
"350": 381,
|
| 456 |
+
"351": 382,
|
| 457 |
+
"352": 383,
|
| 458 |
+
"353": 384,
|
| 459 |
+
"354": 385,
|
| 460 |
+
"355": 386,
|
| 461 |
+
"356": 387,
|
| 462 |
+
"357": 388,
|
| 463 |
+
"358": 389,
|
| 464 |
+
"359": 390,
|
| 465 |
+
"360": 391,
|
| 466 |
+
"361": 392,
|
| 467 |
+
"362": 393,
|
| 468 |
+
"363": 394,
|
| 469 |
+
"364": 395,
|
| 470 |
+
"365": 396,
|
| 471 |
+
"366": 397,
|
| 472 |
+
"367": 398,
|
| 473 |
+
"368": 399,
|
| 474 |
+
"369": 400,
|
| 475 |
+
"370": 401,
|
| 476 |
+
"371": 402,
|
| 477 |
+
"372": 403,
|
| 478 |
+
"373": 404,
|
| 479 |
+
"374": 405,
|
| 480 |
+
"375": 406,
|
| 481 |
+
"376": 407,
|
| 482 |
+
"377": 408,
|
| 483 |
+
"378": 409,
|
| 484 |
+
"379": 410,
|
| 485 |
+
"380": 411,
|
| 486 |
+
"381": 412,
|
| 487 |
+
"382": 413,
|
| 488 |
+
"383": 414,
|
| 489 |
+
"384": 415,
|
| 490 |
+
"385": 416,
|
| 491 |
+
"386": 417,
|
| 492 |
+
"387": 418,
|
| 493 |
+
"388": 419,
|
| 494 |
+
"389": 420,
|
| 495 |
+
"390": 421,
|
| 496 |
+
"391": 422,
|
| 497 |
+
"392": 423,
|
| 498 |
+
"393": 424,
|
| 499 |
+
"394": 425,
|
| 500 |
+
"395": 426,
|
| 501 |
+
"396": 427,
|
| 502 |
+
"397": 428,
|
| 503 |
+
"398": 429,
|
| 504 |
+
"399": 430,
|
| 505 |
+
"400": 431,
|
| 506 |
+
"401": 432,
|
| 507 |
+
"402": 433,
|
| 508 |
+
"403": 434,
|
| 509 |
+
"404": 435,
|
| 510 |
+
"405": 436,
|
| 511 |
+
"406": 437,
|
| 512 |
+
"407": 438,
|
| 513 |
+
"408": 439,
|
| 514 |
+
"409": 440,
|
| 515 |
+
"410": 441,
|
| 516 |
+
"411": 442,
|
| 517 |
+
"412": 443,
|
| 518 |
+
"413": 444,
|
| 519 |
+
"414": 445,
|
| 520 |
+
"415": 446,
|
| 521 |
+
"416": 447,
|
| 522 |
+
"417": 448,
|
| 523 |
+
"418": 449,
|
| 524 |
+
"419": 450,
|
| 525 |
+
"420": 451,
|
| 526 |
+
"421": 452,
|
| 527 |
+
"422": 453,
|
| 528 |
+
"423": 454,
|
| 529 |
+
"424": 455,
|
| 530 |
+
"425": 456,
|
| 531 |
+
"426": 457,
|
| 532 |
+
"427": 458,
|
| 533 |
+
"428": 459,
|
| 534 |
+
"429": 460,
|
| 535 |
+
"430": 461,
|
| 536 |
+
"431": 462,
|
| 537 |
+
"432": 463,
|
| 538 |
+
"433": 464,
|
| 539 |
+
"434": 465,
|
| 540 |
+
"435": 466,
|
| 541 |
+
"436": 467,
|
| 542 |
+
"437": 468,
|
| 543 |
+
"438": 469,
|
| 544 |
+
"439": 470,
|
| 545 |
+
"440": 471,
|
| 546 |
+
"441": 472,
|
| 547 |
+
"442": 473,
|
| 548 |
+
"443": 474,
|
| 549 |
+
"444": 475,
|
| 550 |
+
"445": 476,
|
| 551 |
+
"446": 477,
|
| 552 |
+
"447": 478,
|
| 553 |
+
"448": 479,
|
| 554 |
+
"449": 480,
|
| 555 |
+
"450": 481,
|
| 556 |
+
"451": 482,
|
| 557 |
+
"452": 483,
|
| 558 |
+
"453": 484,
|
| 559 |
+
"454": 485,
|
| 560 |
+
"455": 486,
|
| 561 |
+
"456": 487,
|
| 562 |
+
"457": 488,
|
| 563 |
+
"458": 489,
|
| 564 |
+
"459": 490,
|
| 565 |
+
"460": 491,
|
| 566 |
+
"461": 492,
|
| 567 |
+
"462": 493,
|
| 568 |
+
"463": 494,
|
| 569 |
+
"464": 495,
|
| 570 |
+
"465": 496,
|
| 571 |
+
"466": 497,
|
| 572 |
+
"467": 498,
|
| 573 |
+
"468": 499,
|
| 574 |
+
"469": 500,
|
| 575 |
+
"470": 501,
|
| 576 |
+
"471": 502,
|
| 577 |
+
"472": 503,
|
| 578 |
+
"473": 504,
|
| 579 |
+
"474": 505,
|
| 580 |
+
"475": 506,
|
| 581 |
+
"476": 507,
|
| 582 |
+
"477": 508,
|
| 583 |
+
"478": 509,
|
| 584 |
+
"479": 510,
|
| 585 |
+
"480": 511,
|
| 586 |
+
"481": 512,
|
| 587 |
+
"482": 513,
|
| 588 |
+
"483": 514,
|
| 589 |
+
"484": 515,
|
| 590 |
+
"485": 516,
|
| 591 |
+
"486": 517,
|
| 592 |
+
"487": 518,
|
| 593 |
+
"488": 519,
|
| 594 |
+
"489": 520,
|
| 595 |
+
"490": 521,
|
| 596 |
+
"491": 522,
|
| 597 |
+
"492": 523,
|
| 598 |
+
"493": 524,
|
| 599 |
+
"494": 525,
|
| 600 |
+
"495": 526,
|
| 601 |
+
"496": 527,
|
| 602 |
+
"497": 528,
|
| 603 |
+
"498": 529,
|
| 604 |
+
"499": 530,
|
| 605 |
+
"500": 531,
|
| 606 |
+
"501": 532,
|
| 607 |
+
"502": 533,
|
| 608 |
+
"503": 534,
|
| 609 |
+
"504": 535,
|
| 610 |
+
"505": 536,
|
| 611 |
+
"506": 537,
|
| 612 |
+
"507": 538,
|
| 613 |
+
"508": 539,
|
| 614 |
+
"509": 540,
|
| 615 |
+
"510": 541,
|
| 616 |
+
"511": 542,
|
| 617 |
+
"512": 543,
|
| 618 |
+
"513": 544,
|
| 619 |
+
"514": 545,
|
| 620 |
+
"515": 546,
|
| 621 |
+
"516": 547,
|
| 622 |
+
"517": 548,
|
| 623 |
+
"518": 549,
|
| 624 |
+
"519": 550,
|
| 625 |
+
"520": 551,
|
| 626 |
+
"521": 552,
|
| 627 |
+
"522": 553,
|
| 628 |
+
"523": 554,
|
| 629 |
+
"524": 555,
|
| 630 |
+
"525": 556,
|
| 631 |
+
"526": 557,
|
| 632 |
+
"527": 558,
|
| 633 |
+
"528": 559,
|
| 634 |
+
"529": 560,
|
| 635 |
+
"530": 561,
|
| 636 |
+
"531": 562,
|
| 637 |
+
"532": 563,
|
| 638 |
+
"533": 564,
|
| 639 |
+
"534": 565,
|
| 640 |
+
"535": 566,
|
| 641 |
+
"536": 567,
|
| 642 |
+
"537": 568,
|
| 643 |
+
"538": 569,
|
| 644 |
+
"539": 570,
|
| 645 |
+
"540": 571,
|
| 646 |
+
"541": 572,
|
| 647 |
+
"542": 573,
|
| 648 |
+
"543": 574,
|
| 649 |
+
"544": 575,
|
| 650 |
+
"545": 576,
|
| 651 |
+
"546": 577,
|
| 652 |
+
"547": 578,
|
| 653 |
+
"548": 579,
|
| 654 |
+
"549": 580,
|
| 655 |
+
"550": 581,
|
| 656 |
+
"551": 582,
|
| 657 |
+
"552": 583,
|
| 658 |
+
"553": 584,
|
| 659 |
+
"554": 585,
|
| 660 |
+
"555": 586,
|
| 661 |
+
"556": 587,
|
| 662 |
+
"557": 588,
|
| 663 |
+
"558": 589,
|
| 664 |
+
"559": 590,
|
| 665 |
+
"560": 591,
|
| 666 |
+
"561": 592,
|
| 667 |
+
"562": 593,
|
| 668 |
+
"563": 594,
|
| 669 |
+
"564": 595,
|
| 670 |
+
"565": 596,
|
| 671 |
+
"566": 597,
|
| 672 |
+
"567": 598,
|
| 673 |
+
"568": 599,
|
| 674 |
+
"569": 600,
|
| 675 |
+
"570": 601,
|
| 676 |
+
"571": 602,
|
| 677 |
+
"572": 603,
|
| 678 |
+
"573": 604,
|
| 679 |
+
"574": 605,
|
| 680 |
+
"575": 606,
|
| 681 |
+
"576": 607,
|
| 682 |
+
"577": 608,
|
| 683 |
+
"578": 609,
|
| 684 |
+
"579": 610,
|
| 685 |
+
"580": 611,
|
| 686 |
+
"581": 612,
|
| 687 |
+
"582": 613,
|
| 688 |
+
"583": 614,
|
| 689 |
+
"584": 615,
|
| 690 |
+
"585": 616,
|
| 691 |
+
"586": 617,
|
| 692 |
+
"587": 618,
|
| 693 |
+
"588": 619,
|
| 694 |
+
"589": 620,
|
| 695 |
+
"590": 621,
|
| 696 |
+
"591": 622,
|
| 697 |
+
"592": 623,
|
| 698 |
+
"593": 624,
|
| 699 |
+
"594": 625,
|
| 700 |
+
"595": 626,
|
| 701 |
+
"596": 627,
|
| 702 |
+
"597": 628,
|
| 703 |
+
"598": 629,
|
| 704 |
+
"599": 630,
|
| 705 |
+
"600": 631,
|
| 706 |
+
"|": 632,
|
| 707 |
+
"?": 633
|
| 708 |
+
},
|
| 709 |
+
"unk_token": "[UNK]"
|
| 710 |
+
}
|
| 711 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "_",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[UNK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[BOS]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[EOS]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "[BOS]",
|
| 45 |
+
"clean_up_tokenization_spaces": false,
|
| 46 |
+
"eos_token": "[EOS]",
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "_",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|