Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +516 -0
- tokenizer_config.json +5 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<cls>",
|
3 |
+
"cls_token": "<cls>",
|
4 |
+
"eos_token": "<sep>",
|
5 |
+
"mask_token": "<mask>",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sep_token": "<sep>",
|
8 |
+
"unk_token": "<unk>"
|
9 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<pad>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "<cls>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<sep>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "<unk>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "<mask>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": null,
|
53 |
+
"pre_tokenizer": null,
|
54 |
+
"post_processor": {
|
55 |
+
"type": "TemplateProcessing",
|
56 |
+
"single": [
|
57 |
+
{
|
58 |
+
"SpecialToken": {
|
59 |
+
"id": "<cls>",
|
60 |
+
"type_id": 0
|
61 |
+
}
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"Sequence": {
|
65 |
+
"id": "A",
|
66 |
+
"type_id": 0
|
67 |
+
}
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"SpecialToken": {
|
71 |
+
"id": "<sep>",
|
72 |
+
"type_id": 0
|
73 |
+
}
|
74 |
+
}
|
75 |
+
],
|
76 |
+
"pair": [
|
77 |
+
{
|
78 |
+
"SpecialToken": {
|
79 |
+
"id": "<cls>",
|
80 |
+
"type_id": 0
|
81 |
+
}
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"Sequence": {
|
85 |
+
"id": "A",
|
86 |
+
"type_id": 0
|
87 |
+
}
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"SpecialToken": {
|
91 |
+
"id": "<sep>",
|
92 |
+
"type_id": 0
|
93 |
+
}
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"Sequence": {
|
97 |
+
"id": "B",
|
98 |
+
"type_id": 1
|
99 |
+
}
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"SpecialToken": {
|
103 |
+
"id": "<sep>",
|
104 |
+
"type_id": 1
|
105 |
+
}
|
106 |
+
}
|
107 |
+
],
|
108 |
+
"special_tokens": {
|
109 |
+
"<cls>": {
|
110 |
+
"id": "<cls>",
|
111 |
+
"ids": [
|
112 |
+
1
|
113 |
+
],
|
114 |
+
"tokens": [
|
115 |
+
"<cls>"
|
116 |
+
]
|
117 |
+
},
|
118 |
+
"<sep>": {
|
119 |
+
"id": "<sep>",
|
120 |
+
"ids": [
|
121 |
+
2
|
122 |
+
],
|
123 |
+
"tokens": [
|
124 |
+
"<sep>"
|
125 |
+
]
|
126 |
+
}
|
127 |
+
}
|
128 |
+
},
|
129 |
+
"decoder": {
|
130 |
+
"type": "BPEDecoder",
|
131 |
+
"suffix": "</w>"
|
132 |
+
},
|
133 |
+
"model": {
|
134 |
+
"type": "BPE",
|
135 |
+
"dropout": null,
|
136 |
+
"unk_token": null,
|
137 |
+
"continuing_subword_prefix": null,
|
138 |
+
"end_of_word_suffix": null,
|
139 |
+
"fuse_unk": false,
|
140 |
+
"byte_fallback": false,
|
141 |
+
"vocab": {
|
142 |
+
"<pad>": 0,
|
143 |
+
"<cls>": 1,
|
144 |
+
"<sep>": 2,
|
145 |
+
"<unk>": 3,
|
146 |
+
"<mask>": 4,
|
147 |
+
"A": 5,
|
148 |
+
"B": 6,
|
149 |
+
"C": 7,
|
150 |
+
"D": 8,
|
151 |
+
"E": 9,
|
152 |
+
"F": 10,
|
153 |
+
"G": 11,
|
154 |
+
"H": 12,
|
155 |
+
"I": 13,
|
156 |
+
"K": 14,
|
157 |
+
"L": 15,
|
158 |
+
"M": 16,
|
159 |
+
"N": 17,
|
160 |
+
"O": 18,
|
161 |
+
"P": 19,
|
162 |
+
"Q": 20,
|
163 |
+
"R": 21,
|
164 |
+
"S": 22,
|
165 |
+
"T": 23,
|
166 |
+
"U": 24,
|
167 |
+
"V": 25,
|
168 |
+
"W": 26,
|
169 |
+
"X": 27,
|
170 |
+
"Y": 28,
|
171 |
+
"Z": 29,
|
172 |
+
"AA": 30,
|
173 |
+
"LL": 31,
|
174 |
+
"SS": 32,
|
175 |
+
"LA": 33,
|
176 |
+
"LS": 34,
|
177 |
+
"GG": 35,
|
178 |
+
"LV": 36,
|
179 |
+
"LR": 37,
|
180 |
+
"LE": 38,
|
181 |
+
"LG": 39,
|
182 |
+
"LT": 40,
|
183 |
+
"AV": 41,
|
184 |
+
"AG": 42,
|
185 |
+
"LP": 43,
|
186 |
+
"LD": 44,
|
187 |
+
"LI": 45,
|
188 |
+
"AS": 46,
|
189 |
+
"EE": 47,
|
190 |
+
"RR": 48,
|
191 |
+
"LK": 49,
|
192 |
+
"VV": 50,
|
193 |
+
"AT": 51,
|
194 |
+
"AE": 52,
|
195 |
+
"SG": 53,
|
196 |
+
"DG": 54,
|
197 |
+
"AR": 55,
|
198 |
+
"KK": 56,
|
199 |
+
"AI": 57,
|
200 |
+
"AP": 58,
|
201 |
+
"TT": 59,
|
202 |
+
"LN": 60,
|
203 |
+
"LF": 61,
|
204 |
+
"LQ": 62,
|
205 |
+
"AD": 63,
|
206 |
+
"SV": 64,
|
207 |
+
"ST": 65,
|
208 |
+
"SI": 66,
|
209 |
+
"SP": 67,
|
210 |
+
"DE": 68,
|
211 |
+
"TG": 69,
|
212 |
+
"TV": 70,
|
213 |
+
"SR": 71,
|
214 |
+
"SE": 72,
|
215 |
+
"DV": 73,
|
216 |
+
"PP": 74,
|
217 |
+
"KE": 75,
|
218 |
+
"KI": 76,
|
219 |
+
"DI": 77,
|
220 |
+
"GV": 78,
|
221 |
+
"AQ": 79,
|
222 |
+
"AF": 80,
|
223 |
+
"RV": 81,
|
224 |
+
"TI": 82,
|
225 |
+
"NI": 83,
|
226 |
+
"PV": 84,
|
227 |
+
"RE": 85,
|
228 |
+
"SF": 86,
|
229 |
+
"KV": 87,
|
230 |
+
"NG": 88,
|
231 |
+
"LY": 89,
|
232 |
+
"RI": 90,
|
233 |
+
"PG": 91,
|
234 |
+
"RG": 92,
|
235 |
+
"DD": 93,
|
236 |
+
"PE": 94,
|
237 |
+
"AK": 95,
|
238 |
+
"NV": 96,
|
239 |
+
"SD": 97,
|
240 |
+
"TE": 98,
|
241 |
+
"QQ": 99,
|
242 |
+
"NE": 100,
|
243 |
+
"SK": 101,
|
244 |
+
"LH": 102,
|
245 |
+
"SQ": 103,
|
246 |
+
"GI": 104,
|
247 |
+
"FV": 105,
|
248 |
+
"TP": 106,
|
249 |
+
"GE": 107,
|
250 |
+
"SN": 108,
|
251 |
+
"FI": 109,
|
252 |
+
"AY": 110,
|
253 |
+
"AN": 111,
|
254 |
+
"QV": 112,
|
255 |
+
"RK": 113,
|
256 |
+
"SY": 114,
|
257 |
+
"IV": 115,
|
258 |
+
"FE": 116,
|
259 |
+
"DP": 117,
|
260 |
+
"RP": 118,
|
261 |
+
"IE": 119,
|
262 |
+
"QE": 120,
|
263 |
+
"FG": 121,
|
264 |
+
"LM": 122,
|
265 |
+
"NN": 123,
|
266 |
+
"KG": 124,
|
267 |
+
"RT": 125,
|
268 |
+
"RD": 126,
|
269 |
+
"RQ": 127,
|
270 |
+
"II": 128,
|
271 |
+
"TD": 129,
|
272 |
+
"AH": 130,
|
273 |
+
"AM": 131,
|
274 |
+
"YV": 132,
|
275 |
+
"RF": 133,
|
276 |
+
"EV": 134,
|
277 |
+
"KN": 135,
|
278 |
+
"KD": 136,
|
279 |
+
"IG": 137,
|
280 |
+
"LC": 138,
|
281 |
+
"KT": 139,
|
282 |
+
"KP": 140,
|
283 |
+
"RY": 141,
|
284 |
+
"SH": 142,
|
285 |
+
"QG": 143,
|
286 |
+
"NP": 144,
|
287 |
+
"QI": 145,
|
288 |
+
"FD": 146,
|
289 |
+
"YG": 147,
|
290 |
+
"RN": 148,
|
291 |
+
"YE": 149,
|
292 |
+
"TF": 150,
|
293 |
+
"MV": 151,
|
294 |
+
"RH": 152,
|
295 |
+
"LW": 153,
|
296 |
+
"QP": 154,
|
297 |
+
"TN": 155,
|
298 |
+
"DF": 156,
|
299 |
+
"KQ": 157,
|
300 |
+
"YI": 158,
|
301 |
+
"ME": 159,
|
302 |
+
"VE": 160,
|
303 |
+
"LAA": 161,
|
304 |
+
"PD": 162,
|
305 |
+
"FF": 163,
|
306 |
+
"PI": 164,
|
307 |
+
"AC": 165,
|
308 |
+
"ND": 166,
|
309 |
+
"VG": 167,
|
310 |
+
"TY": 168,
|
311 |
+
"TQ": 169,
|
312 |
+
"SM": 170,
|
313 |
+
"AW": 171,
|
314 |
+
"KY": 172,
|
315 |
+
"HG": 173,
|
316 |
+
"SC": 174,
|
317 |
+
"HV": 175,
|
318 |
+
"ID": 176,
|
319 |
+
"KF": 177,
|
320 |
+
"EG": 178,
|
321 |
+
"KR": 179,
|
322 |
+
"EI": 180,
|
323 |
+
"MG": 181,
|
324 |
+
"TR": 182,
|
325 |
+
"NF": 183,
|
326 |
+
"SW": 184,
|
327 |
+
"TK": 185,
|
328 |
+
"YD": 186,
|
329 |
+
"NQ": 187,
|
330 |
+
"ALL": 188,
|
331 |
+
"MI": 189,
|
332 |
+
"PT": 190,
|
333 |
+
"NY": 191,
|
334 |
+
"QD": 192,
|
335 |
+
"GD": 193,
|
336 |
+
"NT": 194,
|
337 |
+
"HE": 195,
|
338 |
+
"VI": 196,
|
339 |
+
"PF": 197,
|
340 |
+
"ALA": 198,
|
341 |
+
"RS": 199
|
342 |
+
},
|
343 |
+
"merges": [
|
344 |
+
"A A",
|
345 |
+
"L L",
|
346 |
+
"S S",
|
347 |
+
"L A",
|
348 |
+
"L S",
|
349 |
+
"G G",
|
350 |
+
"L V",
|
351 |
+
"L R",
|
352 |
+
"L E",
|
353 |
+
"L G",
|
354 |
+
"L T",
|
355 |
+
"A V",
|
356 |
+
"A G",
|
357 |
+
"L P",
|
358 |
+
"L D",
|
359 |
+
"L I",
|
360 |
+
"A S",
|
361 |
+
"E E",
|
362 |
+
"R R",
|
363 |
+
"L K",
|
364 |
+
"V V",
|
365 |
+
"A T",
|
366 |
+
"A E",
|
367 |
+
"S G",
|
368 |
+
"D G",
|
369 |
+
"A R",
|
370 |
+
"K K",
|
371 |
+
"A I",
|
372 |
+
"A P",
|
373 |
+
"T T",
|
374 |
+
"L N",
|
375 |
+
"L F",
|
376 |
+
"L Q",
|
377 |
+
"A D",
|
378 |
+
"S V",
|
379 |
+
"S T",
|
380 |
+
"S I",
|
381 |
+
"S P",
|
382 |
+
"D E",
|
383 |
+
"T G",
|
384 |
+
"T V",
|
385 |
+
"S R",
|
386 |
+
"S E",
|
387 |
+
"D V",
|
388 |
+
"P P",
|
389 |
+
"K E",
|
390 |
+
"K I",
|
391 |
+
"D I",
|
392 |
+
"G V",
|
393 |
+
"A Q",
|
394 |
+
"A F",
|
395 |
+
"R V",
|
396 |
+
"T I",
|
397 |
+
"N I",
|
398 |
+
"P V",
|
399 |
+
"R E",
|
400 |
+
"S F",
|
401 |
+
"K V",
|
402 |
+
"N G",
|
403 |
+
"L Y",
|
404 |
+
"R I",
|
405 |
+
"P G",
|
406 |
+
"R G",
|
407 |
+
"D D",
|
408 |
+
"P E",
|
409 |
+
"A K",
|
410 |
+
"N V",
|
411 |
+
"S D",
|
412 |
+
"T E",
|
413 |
+
"Q Q",
|
414 |
+
"N E",
|
415 |
+
"S K",
|
416 |
+
"L H",
|
417 |
+
"S Q",
|
418 |
+
"G I",
|
419 |
+
"F V",
|
420 |
+
"T P",
|
421 |
+
"G E",
|
422 |
+
"S N",
|
423 |
+
"F I",
|
424 |
+
"A Y",
|
425 |
+
"A N",
|
426 |
+
"Q V",
|
427 |
+
"R K",
|
428 |
+
"S Y",
|
429 |
+
"I V",
|
430 |
+
"F E",
|
431 |
+
"D P",
|
432 |
+
"R P",
|
433 |
+
"I E",
|
434 |
+
"Q E",
|
435 |
+
"F G",
|
436 |
+
"L M",
|
437 |
+
"N N",
|
438 |
+
"K G",
|
439 |
+
"R T",
|
440 |
+
"R D",
|
441 |
+
"R Q",
|
442 |
+
"I I",
|
443 |
+
"T D",
|
444 |
+
"A H",
|
445 |
+
"A M",
|
446 |
+
"Y V",
|
447 |
+
"R F",
|
448 |
+
"E V",
|
449 |
+
"K N",
|
450 |
+
"K D",
|
451 |
+
"I G",
|
452 |
+
"L C",
|
453 |
+
"K T",
|
454 |
+
"K P",
|
455 |
+
"R Y",
|
456 |
+
"S H",
|
457 |
+
"Q G",
|
458 |
+
"N P",
|
459 |
+
"Q I",
|
460 |
+
"F D",
|
461 |
+
"Y G",
|
462 |
+
"R N",
|
463 |
+
"Y E",
|
464 |
+
"T F",
|
465 |
+
"M V",
|
466 |
+
"R H",
|
467 |
+
"L W",
|
468 |
+
"Q P",
|
469 |
+
"T N",
|
470 |
+
"D F",
|
471 |
+
"K Q",
|
472 |
+
"Y I",
|
473 |
+
"M E",
|
474 |
+
"V E",
|
475 |
+
"L AA",
|
476 |
+
"P D",
|
477 |
+
"F F",
|
478 |
+
"P I",
|
479 |
+
"A C",
|
480 |
+
"N D",
|
481 |
+
"V G",
|
482 |
+
"T Y",
|
483 |
+
"T Q",
|
484 |
+
"S M",
|
485 |
+
"A W",
|
486 |
+
"K Y",
|
487 |
+
"H G",
|
488 |
+
"S C",
|
489 |
+
"H V",
|
490 |
+
"I D",
|
491 |
+
"K F",
|
492 |
+
"E G",
|
493 |
+
"K R",
|
494 |
+
"E I",
|
495 |
+
"M G",
|
496 |
+
"T R",
|
497 |
+
"N F",
|
498 |
+
"S W",
|
499 |
+
"T K",
|
500 |
+
"Y D",
|
501 |
+
"N Q",
|
502 |
+
"A LL",
|
503 |
+
"M I",
|
504 |
+
"P T",
|
505 |
+
"N Y",
|
506 |
+
"Q D",
|
507 |
+
"G D",
|
508 |
+
"N T",
|
509 |
+
"H E",
|
510 |
+
"V I",
|
511 |
+
"P F",
|
512 |
+
"A LA",
|
513 |
+
"R S"
|
514 |
+
]
|
515 |
+
}
|
516 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
5 |
+
}
|