lhallee commited on
Commit
c73d1b7
1 Parent(s): 826188b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +124 -0
  2. tokenizer.json +1723 -0
  3. tokenizer_config.json +1082 -0
special_tokens_map.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "<extra_id_100>",
104
+ "<extra_id_101>",
105
+ "<extra_id_102>",
106
+ "<extra_id_103>",
107
+ "<extra_id_104>",
108
+ "<extra_id_105>",
109
+ "<extra_id_106>",
110
+ "<extra_id_107>",
111
+ "<extra_id_108>",
112
+ "<extra_id_109>",
113
+ "<extra_id_110>",
114
+ "<extra_id_111>",
115
+ "<extra_id_112>",
116
+ "<extra_id_113>",
117
+ "<extra_id_114>",
118
+ "<extra_id_115>"
119
+ ],
120
+ "eos_token": "</s>",
121
+ "mask_token": "<extra_id_0>",
122
+ "pad_token": "<pad>",
123
+ "unk_token": "<unk>"
124
+ }
tokenizer.json ADDED
@@ -0,0 +1,1723 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
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": 28,
35
+ "content": "<extra_id_115>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 29,
44
+ "content": "<extra_id_114>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 30,
53
+ "content": "<extra_id_113>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 31,
62
+ "content": "<extra_id_112>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 32,
71
+ "content": "<extra_id_111>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 33,
80
+ "content": "<extra_id_110>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 34,
89
+ "content": "<extra_id_109>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 35,
98
+ "content": "<extra_id_108>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 36,
107
+ "content": "<extra_id_107>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 37,
116
+ "content": "<extra_id_106>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 38,
125
+ "content": "<extra_id_105>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 39,
134
+ "content": "<extra_id_104>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 40,
143
+ "content": "<extra_id_103>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 41,
152
+ "content": "<extra_id_102>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 42,
161
+ "content": "<extra_id_101>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 43,
170
+ "content": "<extra_id_100>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 44,
179
+ "content": "<extra_id_99>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 45,
188
+ "content": "<extra_id_98>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 46,
197
+ "content": "<extra_id_97>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 47,
206
+ "content": "<extra_id_96>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 48,
215
+ "content": "<extra_id_95>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 49,
224
+ "content": "<extra_id_94>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 50,
233
+ "content": "<extra_id_93>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 51,
242
+ "content": "<extra_id_92>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 52,
251
+ "content": "<extra_id_91>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 53,
260
+ "content": "<extra_id_90>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 54,
269
+ "content": "<extra_id_89>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 55,
278
+ "content": "<extra_id_88>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 56,
287
+ "content": "<extra_id_87>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 57,
296
+ "content": "<extra_id_86>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 58,
305
+ "content": "<extra_id_85>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 59,
314
+ "content": "<extra_id_84>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 60,
323
+ "content": "<extra_id_83>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 61,
332
+ "content": "<extra_id_82>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 62,
341
+ "content": "<extra_id_81>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 63,
350
+ "content": "<extra_id_80>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 64,
359
+ "content": "<extra_id_79>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 65,
368
+ "content": "<extra_id_78>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 66,
377
+ "content": "<extra_id_77>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 67,
386
+ "content": "<extra_id_76>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 68,
395
+ "content": "<extra_id_75>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 69,
404
+ "content": "<extra_id_74>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 70,
413
+ "content": "<extra_id_73>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 71,
422
+ "content": "<extra_id_72>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 72,
431
+ "content": "<extra_id_71>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 73,
440
+ "content": "<extra_id_70>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 74,
449
+ "content": "<extra_id_69>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 75,
458
+ "content": "<extra_id_68>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 76,
467
+ "content": "<extra_id_67>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 77,
476
+ "content": "<extra_id_66>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 78,
485
+ "content": "<extra_id_65>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 79,
494
+ "content": "<extra_id_64>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 80,
503
+ "content": "<extra_id_63>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 81,
512
+ "content": "<extra_id_62>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 82,
521
+ "content": "<extra_id_61>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 83,
530
+ "content": "<extra_id_60>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 84,
539
+ "content": "<extra_id_59>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 85,
548
+ "content": "<extra_id_58>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 86,
557
+ "content": "<extra_id_57>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 87,
566
+ "content": "<extra_id_56>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 88,
575
+ "content": "<extra_id_55>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 89,
584
+ "content": "<extra_id_54>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 90,
593
+ "content": "<extra_id_53>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 91,
602
+ "content": "<extra_id_52>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 92,
611
+ "content": "<extra_id_51>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 93,
620
+ "content": "<extra_id_50>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 94,
629
+ "content": "<extra_id_49>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 95,
638
+ "content": "<extra_id_48>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 96,
647
+ "content": "<extra_id_47>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 97,
656
+ "content": "<extra_id_46>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 98,
665
+ "content": "<extra_id_45>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 99,
674
+ "content": "<extra_id_44>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 100,
683
+ "content": "<extra_id_43>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 101,
692
+ "content": "<extra_id_42>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 102,
701
+ "content": "<extra_id_41>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 103,
710
+ "content": "<extra_id_40>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 104,
719
+ "content": "<extra_id_39>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 105,
728
+ "content": "<extra_id_38>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 106,
737
+ "content": "<extra_id_37>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 107,
746
+ "content": "<extra_id_36>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 108,
755
+ "content": "<extra_id_35>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 109,
764
+ "content": "<extra_id_34>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 110,
773
+ "content": "<extra_id_33>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 111,
782
+ "content": "<extra_id_32>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 112,
791
+ "content": "<extra_id_31>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 113,
800
+ "content": "<extra_id_30>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 114,
809
+ "content": "<extra_id_29>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 115,
818
+ "content": "<extra_id_28>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 116,
827
+ "content": "<extra_id_27>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 117,
836
+ "content": "<extra_id_26>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 118,
845
+ "content": "<extra_id_25>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 119,
854
+ "content": "<extra_id_24>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 120,
863
+ "content": "<extra_id_23>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 121,
872
+ "content": "<extra_id_22>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 122,
881
+ "content": "<extra_id_21>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 123,
890
+ "content": "<extra_id_20>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 124,
899
+ "content": "<extra_id_19>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 125,
908
+ "content": "<extra_id_18>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 126,
917
+ "content": "<extra_id_17>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 127,
926
+ "content": "<extra_id_16>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 128,
935
+ "content": "<extra_id_15>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ },
942
+ {
943
+ "id": 129,
944
+ "content": "<extra_id_14>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 130,
953
+ "content": "<extra_id_13>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 131,
962
+ "content": "<extra_id_12>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 132,
971
+ "content": "<extra_id_11>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 133,
980
+ "content": "<extra_id_10>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 134,
989
+ "content": "<extra_id_9>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 135,
998
+ "content": "<extra_id_8>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 136,
1007
+ "content": "<extra_id_7>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 137,
1016
+ "content": "<extra_id_6>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 138,
1025
+ "content": "<extra_id_5>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 139,
1034
+ "content": "<extra_id_4>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 140,
1043
+ "content": "<extra_id_3>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 141,
1052
+ "content": "<extra_id_2>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 142,
1061
+ "content": "<extra_id_1>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 143,
1070
+ "content": "<extra_id_0>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ }
1077
+ ],
1078
+ "normalizer": null,
1079
+ "pre_tokenizer": null,
1080
+ "post_processor": {
1081
+ "type": "TemplateProcessing",
1082
+ "single": [
1083
+ {
1084
+ "Sequence": {
1085
+ "id": "A",
1086
+ "type_id": 0
1087
+ }
1088
+ },
1089
+ {
1090
+ "SpecialToken": {
1091
+ "id": "</s>",
1092
+ "type_id": 0
1093
+ }
1094
+ }
1095
+ ],
1096
+ "pair": [
1097
+ {
1098
+ "Sequence": {
1099
+ "id": "A",
1100
+ "type_id": 0
1101
+ }
1102
+ },
1103
+ {
1104
+ "SpecialToken": {
1105
+ "id": "</s>",
1106
+ "type_id": 0
1107
+ }
1108
+ },
1109
+ {
1110
+ "Sequence": {
1111
+ "id": "B",
1112
+ "type_id": 0
1113
+ }
1114
+ },
1115
+ {
1116
+ "SpecialToken": {
1117
+ "id": "</s>",
1118
+ "type_id": 0
1119
+ }
1120
+ }
1121
+ ],
1122
+ "special_tokens": {
1123
+ "</s>": {
1124
+ "id": "</s>",
1125
+ "ids": [
1126
+ 1
1127
+ ],
1128
+ "tokens": [
1129
+ "</s>"
1130
+ ]
1131
+ }
1132
+ }
1133
+ },
1134
+ "decoder": {
1135
+ "type": "Metaspace",
1136
+ "replacement": "▁",
1137
+ "add_prefix_space": true,
1138
+ "prepend_scheme": "always"
1139
+ },
1140
+ "model": {
1141
+ "type": "Unigram",
1142
+ "unk_id": 2,
1143
+ "vocab": [
1144
+ [
1145
+ "<pad>",
1146
+ 0.0
1147
+ ],
1148
+ [
1149
+ "</s>",
1150
+ 0.0
1151
+ ],
1152
+ [
1153
+ "<unk>",
1154
+ 0.0
1155
+ ],
1156
+ [
1157
+ "A",
1158
+ -2.2783124446868896
1159
+ ],
1160
+ [
1161
+ "L",
1162
+ -2.3026247024536133
1163
+ ],
1164
+ [
1165
+ "G",
1166
+ -2.57137393951416
1167
+ ],
1168
+ [
1169
+ "V",
1170
+ -2.649644136428833
1171
+ ],
1172
+ [
1173
+ "S",
1174
+ -2.734614133834839
1175
+ ],
1176
+ [
1177
+ "R",
1178
+ -2.783693790435791
1179
+ ],
1180
+ [
1181
+ "E",
1182
+ -2.803671598434448
1183
+ ],
1184
+ [
1185
+ "D",
1186
+ -2.8803412914276123
1187
+ ],
1188
+ [
1189
+ "T",
1190
+ -2.903266429901123
1191
+ ],
1192
+ [
1193
+ "I",
1194
+ -2.9337375164031982
1195
+ ],
1196
+ [
1197
+ "P",
1198
+ -2.98986291885376
1199
+ ],
1200
+ [
1201
+ "K",
1202
+ -3.110422134399414
1203
+ ],
1204
+ [
1205
+ "F",
1206
+ -3.282776355743408
1207
+ ],
1208
+ [
1209
+ "Q",
1210
+ -3.3202931880950928
1211
+ ],
1212
+ [
1213
+ "N",
1214
+ -3.351658582687378
1215
+ ],
1216
+ [
1217
+ "Y",
1218
+ -3.605137825012207
1219
+ ],
1220
+ [
1221
+ "M",
1222
+ -3.781080961227417
1223
+ ],
1224
+ [
1225
+ "H",
1226
+ -3.8282647132873535
1227
+ ],
1228
+ [
1229
+ "W",
1230
+ -4.356028079986572
1231
+ ],
1232
+ [
1233
+ "C",
1234
+ -4.526663780212402
1235
+ ],
1236
+ [
1237
+ "X",
1238
+ -10.67774772644043
1239
+ ],
1240
+ [
1241
+ "B",
1242
+ -16.226823806762695
1243
+ ],
1244
+ [
1245
+ "O",
1246
+ -16.226823806762695
1247
+ ],
1248
+ [
1249
+ "U",
1250
+ -16.226823806762695
1251
+ ],
1252
+ [
1253
+ "Z",
1254
+ -16.226823806762695
1255
+ ],
1256
+ [
1257
+ "<extra_id_115>",
1258
+ 0.0
1259
+ ],
1260
+ [
1261
+ "<extra_id_114>",
1262
+ 0.0
1263
+ ],
1264
+ [
1265
+ "<extra_id_113>",
1266
+ 0.0
1267
+ ],
1268
+ [
1269
+ "<extra_id_112>",
1270
+ 0.0
1271
+ ],
1272
+ [
1273
+ "<extra_id_111>",
1274
+ 0.0
1275
+ ],
1276
+ [
1277
+ "<extra_id_110>",
1278
+ 0.0
1279
+ ],
1280
+ [
1281
+ "<extra_id_109>",
1282
+ 0.0
1283
+ ],
1284
+ [
1285
+ "<extra_id_108>",
1286
+ 0.0
1287
+ ],
1288
+ [
1289
+ "<extra_id_107>",
1290
+ 0.0
1291
+ ],
1292
+ [
1293
+ "<extra_id_106>",
1294
+ 0.0
1295
+ ],
1296
+ [
1297
+ "<extra_id_105>",
1298
+ 0.0
1299
+ ],
1300
+ [
1301
+ "<extra_id_104>",
1302
+ 0.0
1303
+ ],
1304
+ [
1305
+ "<extra_id_103>",
1306
+ 0.0
1307
+ ],
1308
+ [
1309
+ "<extra_id_102>",
1310
+ 0.0
1311
+ ],
1312
+ [
1313
+ "<extra_id_101>",
1314
+ 0.0
1315
+ ],
1316
+ [
1317
+ "<extra_id_100>",
1318
+ 0.0
1319
+ ],
1320
+ [
1321
+ "<extra_id_99>",
1322
+ 0.0
1323
+ ],
1324
+ [
1325
+ "<extra_id_98>",
1326
+ 0.0
1327
+ ],
1328
+ [
1329
+ "<extra_id_97>",
1330
+ 0.0
1331
+ ],
1332
+ [
1333
+ "<extra_id_96>",
1334
+ 0.0
1335
+ ],
1336
+ [
1337
+ "<extra_id_95>",
1338
+ 0.0
1339
+ ],
1340
+ [
1341
+ "<extra_id_94>",
1342
+ 0.0
1343
+ ],
1344
+ [
1345
+ "<extra_id_93>",
1346
+ 0.0
1347
+ ],
1348
+ [
1349
+ "<extra_id_92>",
1350
+ 0.0
1351
+ ],
1352
+ [
1353
+ "<extra_id_91>",
1354
+ 0.0
1355
+ ],
1356
+ [
1357
+ "<extra_id_90>",
1358
+ 0.0
1359
+ ],
1360
+ [
1361
+ "<extra_id_89>",
1362
+ 0.0
1363
+ ],
1364
+ [
1365
+ "<extra_id_88>",
1366
+ 0.0
1367
+ ],
1368
+ [
1369
+ "<extra_id_87>",
1370
+ 0.0
1371
+ ],
1372
+ [
1373
+ "<extra_id_86>",
1374
+ 0.0
1375
+ ],
1376
+ [
1377
+ "<extra_id_85>",
1378
+ 0.0
1379
+ ],
1380
+ [
1381
+ "<extra_id_84>",
1382
+ 0.0
1383
+ ],
1384
+ [
1385
+ "<extra_id_83>",
1386
+ 0.0
1387
+ ],
1388
+ [
1389
+ "<extra_id_82>",
1390
+ 0.0
1391
+ ],
1392
+ [
1393
+ "<extra_id_81>",
1394
+ 0.0
1395
+ ],
1396
+ [
1397
+ "<extra_id_80>",
1398
+ 0.0
1399
+ ],
1400
+ [
1401
+ "<extra_id_79>",
1402
+ 0.0
1403
+ ],
1404
+ [
1405
+ "<extra_id_78>",
1406
+ 0.0
1407
+ ],
1408
+ [
1409
+ "<extra_id_77>",
1410
+ 0.0
1411
+ ],
1412
+ [
1413
+ "<extra_id_76>",
1414
+ 0.0
1415
+ ],
1416
+ [
1417
+ "<extra_id_75>",
1418
+ 0.0
1419
+ ],
1420
+ [
1421
+ "<extra_id_74>",
1422
+ 0.0
1423
+ ],
1424
+ [
1425
+ "<extra_id_73>",
1426
+ 0.0
1427
+ ],
1428
+ [
1429
+ "<extra_id_72>",
1430
+ 0.0
1431
+ ],
1432
+ [
1433
+ "<extra_id_71>",
1434
+ 0.0
1435
+ ],
1436
+ [
1437
+ "<extra_id_70>",
1438
+ 0.0
1439
+ ],
1440
+ [
1441
+ "<extra_id_69>",
1442
+ 0.0
1443
+ ],
1444
+ [
1445
+ "<extra_id_68>",
1446
+ 0.0
1447
+ ],
1448
+ [
1449
+ "<extra_id_67>",
1450
+ 0.0
1451
+ ],
1452
+ [
1453
+ "<extra_id_66>",
1454
+ 0.0
1455
+ ],
1456
+ [
1457
+ "<extra_id_65>",
1458
+ 0.0
1459
+ ],
1460
+ [
1461
+ "<extra_id_64>",
1462
+ 0.0
1463
+ ],
1464
+ [
1465
+ "<extra_id_63>",
1466
+ 0.0
1467
+ ],
1468
+ [
1469
+ "<extra_id_62>",
1470
+ 0.0
1471
+ ],
1472
+ [
1473
+ "<extra_id_61>",
1474
+ 0.0
1475
+ ],
1476
+ [
1477
+ "<extra_id_60>",
1478
+ 0.0
1479
+ ],
1480
+ [
1481
+ "<extra_id_59>",
1482
+ 0.0
1483
+ ],
1484
+ [
1485
+ "<extra_id_58>",
1486
+ 0.0
1487
+ ],
1488
+ [
1489
+ "<extra_id_57>",
1490
+ 0.0
1491
+ ],
1492
+ [
1493
+ "<extra_id_56>",
1494
+ 0.0
1495
+ ],
1496
+ [
1497
+ "<extra_id_55>",
1498
+ 0.0
1499
+ ],
1500
+ [
1501
+ "<extra_id_54>",
1502
+ 0.0
1503
+ ],
1504
+ [
1505
+ "<extra_id_53>",
1506
+ 0.0
1507
+ ],
1508
+ [
1509
+ "<extra_id_52>",
1510
+ 0.0
1511
+ ],
1512
+ [
1513
+ "<extra_id_51>",
1514
+ 0.0
1515
+ ],
1516
+ [
1517
+ "<extra_id_50>",
1518
+ 0.0
1519
+ ],
1520
+ [
1521
+ "<extra_id_49>",
1522
+ 0.0
1523
+ ],
1524
+ [
1525
+ "<extra_id_48>",
1526
+ 0.0
1527
+ ],
1528
+ [
1529
+ "<extra_id_47>",
1530
+ 0.0
1531
+ ],
1532
+ [
1533
+ "<extra_id_46>",
1534
+ 0.0
1535
+ ],
1536
+ [
1537
+ "<extra_id_45>",
1538
+ 0.0
1539
+ ],
1540
+ [
1541
+ "<extra_id_44>",
1542
+ 0.0
1543
+ ],
1544
+ [
1545
+ "<extra_id_43>",
1546
+ 0.0
1547
+ ],
1548
+ [
1549
+ "<extra_id_42>",
1550
+ 0.0
1551
+ ],
1552
+ [
1553
+ "<extra_id_41>",
1554
+ 0.0
1555
+ ],
1556
+ [
1557
+ "<extra_id_40>",
1558
+ 0.0
1559
+ ],
1560
+ [
1561
+ "<extra_id_39>",
1562
+ 0.0
1563
+ ],
1564
+ [
1565
+ "<extra_id_38>",
1566
+ 0.0
1567
+ ],
1568
+ [
1569
+ "<extra_id_37>",
1570
+ 0.0
1571
+ ],
1572
+ [
1573
+ "<extra_id_36>",
1574
+ 0.0
1575
+ ],
1576
+ [
1577
+ "<extra_id_35>",
1578
+ 0.0
1579
+ ],
1580
+ [
1581
+ "<extra_id_34>",
1582
+ 0.0
1583
+ ],
1584
+ [
1585
+ "<extra_id_33>",
1586
+ 0.0
1587
+ ],
1588
+ [
1589
+ "<extra_id_32>",
1590
+ 0.0
1591
+ ],
1592
+ [
1593
+ "<extra_id_31>",
1594
+ 0.0
1595
+ ],
1596
+ [
1597
+ "<extra_id_30>",
1598
+ 0.0
1599
+ ],
1600
+ [
1601
+ "<extra_id_29>",
1602
+ 0.0
1603
+ ],
1604
+ [
1605
+ "<extra_id_28>",
1606
+ 0.0
1607
+ ],
1608
+ [
1609
+ "<extra_id_27>",
1610
+ 0.0
1611
+ ],
1612
+ [
1613
+ "<extra_id_26>",
1614
+ 0.0
1615
+ ],
1616
+ [
1617
+ "<extra_id_25>",
1618
+ 0.0
1619
+ ],
1620
+ [
1621
+ "<extra_id_24>",
1622
+ 0.0
1623
+ ],
1624
+ [
1625
+ "<extra_id_23>",
1626
+ 0.0
1627
+ ],
1628
+ [
1629
+ "<extra_id_22>",
1630
+ 0.0
1631
+ ],
1632
+ [
1633
+ "<extra_id_21>",
1634
+ 0.0
1635
+ ],
1636
+ [
1637
+ "<extra_id_20>",
1638
+ 0.0
1639
+ ],
1640
+ [
1641
+ "<extra_id_19>",
1642
+ 0.0
1643
+ ],
1644
+ [
1645
+ "<extra_id_18>",
1646
+ 0.0
1647
+ ],
1648
+ [
1649
+ "<extra_id_17>",
1650
+ 0.0
1651
+ ],
1652
+ [
1653
+ "<extra_id_16>",
1654
+ 0.0
1655
+ ],
1656
+ [
1657
+ "<extra_id_15>",
1658
+ 0.0
1659
+ ],
1660
+ [
1661
+ "<extra_id_14>",
1662
+ 0.0
1663
+ ],
1664
+ [
1665
+ "<extra_id_13>",
1666
+ 0.0
1667
+ ],
1668
+ [
1669
+ "<extra_id_12>",
1670
+ 0.0
1671
+ ],
1672
+ [
1673
+ "<extra_id_11>",
1674
+ 0.0
1675
+ ],
1676
+ [
1677
+ "<extra_id_10>",
1678
+ 0.0
1679
+ ],
1680
+ [
1681
+ "<extra_id_9>",
1682
+ 0.0
1683
+ ],
1684
+ [
1685
+ "<extra_id_8>",
1686
+ 0.0
1687
+ ],
1688
+ [
1689
+ "<extra_id_7>",
1690
+ 0.0
1691
+ ],
1692
+ [
1693
+ "<extra_id_6>",
1694
+ 0.0
1695
+ ],
1696
+ [
1697
+ "<extra_id_5>",
1698
+ 0.0
1699
+ ],
1700
+ [
1701
+ "<extra_id_4>",
1702
+ 0.0
1703
+ ],
1704
+ [
1705
+ "<extra_id_3>",
1706
+ 0.0
1707
+ ],
1708
+ [
1709
+ "<extra_id_2>",
1710
+ 0.0
1711
+ ],
1712
+ [
1713
+ "<extra_id_1>",
1714
+ 0.0
1715
+ ],
1716
+ [
1717
+ "<extra_id_0>",
1718
+ 0.0
1719
+ ]
1720
+ ],
1721
+ "byte_fallback": false
1722
+ }
1723
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,1082 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
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
+ "28": {
28
+ "content": "<extra_id_115>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "29": {
36
+ "content": "<extra_id_114>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30": {
44
+ "content": "<extra_id_113>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "31": {
52
+ "content": "<extra_id_112>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32": {
60
+ "content": "<extra_id_111>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "33": {
68
+ "content": "<extra_id_110>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "34": {
76
+ "content": "<extra_id_109>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "35": {
84
+ "content": "<extra_id_108>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "36": {
92
+ "content": "<extra_id_107>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "37": {
100
+ "content": "<extra_id_106>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "38": {
108
+ "content": "<extra_id_105>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "39": {
116
+ "content": "<extra_id_104>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "40": {
124
+ "content": "<extra_id_103>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "41": {
132
+ "content": "<extra_id_102>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "42": {
140
+ "content": "<extra_id_101>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "43": {
148
+ "content": "<extra_id_100>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "44": {
156
+ "content": "<extra_id_99>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "45": {
164
+ "content": "<extra_id_98>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "46": {
172
+ "content": "<extra_id_97>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "47": {
180
+ "content": "<extra_id_96>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "48": {
188
+ "content": "<extra_id_95>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "49": {
196
+ "content": "<extra_id_94>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "50": {
204
+ "content": "<extra_id_93>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "51": {
212
+ "content": "<extra_id_92>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "52": {
220
+ "content": "<extra_id_91>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "53": {
228
+ "content": "<extra_id_90>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "54": {
236
+ "content": "<extra_id_89>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "55": {
244
+ "content": "<extra_id_88>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "56": {
252
+ "content": "<extra_id_87>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "57": {
260
+ "content": "<extra_id_86>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "58": {
268
+ "content": "<extra_id_85>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "59": {
276
+ "content": "<extra_id_84>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "60": {
284
+ "content": "<extra_id_83>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "61": {
292
+ "content": "<extra_id_82>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "62": {
300
+ "content": "<extra_id_81>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "63": {
308
+ "content": "<extra_id_80>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "64": {
316
+ "content": "<extra_id_79>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "65": {
324
+ "content": "<extra_id_78>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "66": {
332
+ "content": "<extra_id_77>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "67": {
340
+ "content": "<extra_id_76>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "68": {
348
+ "content": "<extra_id_75>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "69": {
356
+ "content": "<extra_id_74>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "70": {
364
+ "content": "<extra_id_73>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "71": {
372
+ "content": "<extra_id_72>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "72": {
380
+ "content": "<extra_id_71>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "73": {
388
+ "content": "<extra_id_70>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "74": {
396
+ "content": "<extra_id_69>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "75": {
404
+ "content": "<extra_id_68>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "76": {
412
+ "content": "<extra_id_67>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "77": {
420
+ "content": "<extra_id_66>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "78": {
428
+ "content": "<extra_id_65>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "79": {
436
+ "content": "<extra_id_64>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "80": {
444
+ "content": "<extra_id_63>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "81": {
452
+ "content": "<extra_id_62>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "82": {
460
+ "content": "<extra_id_61>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "83": {
468
+ "content": "<extra_id_60>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "84": {
476
+ "content": "<extra_id_59>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "85": {
484
+ "content": "<extra_id_58>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "86": {
492
+ "content": "<extra_id_57>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "87": {
500
+ "content": "<extra_id_56>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "88": {
508
+ "content": "<extra_id_55>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "89": {
516
+ "content": "<extra_id_54>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "90": {
524
+ "content": "<extra_id_53>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "91": {
532
+ "content": "<extra_id_52>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "92": {
540
+ "content": "<extra_id_51>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "93": {
548
+ "content": "<extra_id_50>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "94": {
556
+ "content": "<extra_id_49>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "95": {
564
+ "content": "<extra_id_48>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "96": {
572
+ "content": "<extra_id_47>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "97": {
580
+ "content": "<extra_id_46>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "98": {
588
+ "content": "<extra_id_45>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "99": {
596
+ "content": "<extra_id_44>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "100": {
604
+ "content": "<extra_id_43>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "101": {
612
+ "content": "<extra_id_42>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "102": {
620
+ "content": "<extra_id_41>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "103": {
628
+ "content": "<extra_id_40>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "104": {
636
+ "content": "<extra_id_39>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "105": {
644
+ "content": "<extra_id_38>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "106": {
652
+ "content": "<extra_id_37>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "107": {
660
+ "content": "<extra_id_36>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "108": {
668
+ "content": "<extra_id_35>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "109": {
676
+ "content": "<extra_id_34>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "110": {
684
+ "content": "<extra_id_33>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "111": {
692
+ "content": "<extra_id_32>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "112": {
700
+ "content": "<extra_id_31>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "113": {
708
+ "content": "<extra_id_30>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "114": {
716
+ "content": "<extra_id_29>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "115": {
724
+ "content": "<extra_id_28>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "116": {
732
+ "content": "<extra_id_27>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "117": {
740
+ "content": "<extra_id_26>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "118": {
748
+ "content": "<extra_id_25>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "119": {
756
+ "content": "<extra_id_24>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "120": {
764
+ "content": "<extra_id_23>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "121": {
772
+ "content": "<extra_id_22>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "122": {
780
+ "content": "<extra_id_21>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "123": {
788
+ "content": "<extra_id_20>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "124": {
796
+ "content": "<extra_id_19>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "125": {
804
+ "content": "<extra_id_18>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "126": {
812
+ "content": "<extra_id_17>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "127": {
820
+ "content": "<extra_id_16>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128": {
828
+ "content": "<extra_id_15>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "129": {
836
+ "content": "<extra_id_14>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "130": {
844
+ "content": "<extra_id_13>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "131": {
852
+ "content": "<extra_id_12>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "132": {
860
+ "content": "<extra_id_11>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "133": {
868
+ "content": "<extra_id_10>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "134": {
876
+ "content": "<extra_id_9>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "135": {
884
+ "content": "<extra_id_8>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "136": {
892
+ "content": "<extra_id_7>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "137": {
900
+ "content": "<extra_id_6>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "138": {
908
+ "content": "<extra_id_5>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "139": {
916
+ "content": "<extra_id_4>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "140": {
924
+ "content": "<extra_id_3>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "141": {
932
+ "content": "<extra_id_2>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "142": {
940
+ "content": "<extra_id_1>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "143": {
948
+ "content": "<extra_id_0>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ }
955
+ },
956
+ "additional_special_tokens": [
957
+ "<extra_id_0>",
958
+ "<extra_id_1>",
959
+ "<extra_id_2>",
960
+ "<extra_id_3>",
961
+ "<extra_id_4>",
962
+ "<extra_id_5>",
963
+ "<extra_id_6>",
964
+ "<extra_id_7>",
965
+ "<extra_id_8>",
966
+ "<extra_id_9>",
967
+ "<extra_id_10>",
968
+ "<extra_id_11>",
969
+ "<extra_id_12>",
970
+ "<extra_id_13>",
971
+ "<extra_id_14>",
972
+ "<extra_id_15>",
973
+ "<extra_id_16>",
974
+ "<extra_id_17>",
975
+ "<extra_id_18>",
976
+ "<extra_id_19>",
977
+ "<extra_id_20>",
978
+ "<extra_id_21>",
979
+ "<extra_id_22>",
980
+ "<extra_id_23>",
981
+ "<extra_id_24>",
982
+ "<extra_id_25>",
983
+ "<extra_id_26>",
984
+ "<extra_id_27>",
985
+ "<extra_id_28>",
986
+ "<extra_id_29>",
987
+ "<extra_id_30>",
988
+ "<extra_id_31>",
989
+ "<extra_id_32>",
990
+ "<extra_id_33>",
991
+ "<extra_id_34>",
992
+ "<extra_id_35>",
993
+ "<extra_id_36>",
994
+ "<extra_id_37>",
995
+ "<extra_id_38>",
996
+ "<extra_id_39>",
997
+ "<extra_id_40>",
998
+ "<extra_id_41>",
999
+ "<extra_id_42>",
1000
+ "<extra_id_43>",
1001
+ "<extra_id_44>",
1002
+ "<extra_id_45>",
1003
+ "<extra_id_46>",
1004
+ "<extra_id_47>",
1005
+ "<extra_id_48>",
1006
+ "<extra_id_49>",
1007
+ "<extra_id_50>",
1008
+ "<extra_id_51>",
1009
+ "<extra_id_52>",
1010
+ "<extra_id_53>",
1011
+ "<extra_id_54>",
1012
+ "<extra_id_55>",
1013
+ "<extra_id_56>",
1014
+ "<extra_id_57>",
1015
+ "<extra_id_58>",
1016
+ "<extra_id_59>",
1017
+ "<extra_id_60>",
1018
+ "<extra_id_61>",
1019
+ "<extra_id_62>",
1020
+ "<extra_id_63>",
1021
+ "<extra_id_64>",
1022
+ "<extra_id_65>",
1023
+ "<extra_id_66>",
1024
+ "<extra_id_67>",
1025
+ "<extra_id_68>",
1026
+ "<extra_id_69>",
1027
+ "<extra_id_70>",
1028
+ "<extra_id_71>",
1029
+ "<extra_id_72>",
1030
+ "<extra_id_73>",
1031
+ "<extra_id_74>",
1032
+ "<extra_id_75>",
1033
+ "<extra_id_76>",
1034
+ "<extra_id_77>",
1035
+ "<extra_id_78>",
1036
+ "<extra_id_79>",
1037
+ "<extra_id_80>",
1038
+ "<extra_id_81>",
1039
+ "<extra_id_82>",
1040
+ "<extra_id_83>",
1041
+ "<extra_id_84>",
1042
+ "<extra_id_85>",
1043
+ "<extra_id_86>",
1044
+ "<extra_id_87>",
1045
+ "<extra_id_88>",
1046
+ "<extra_id_89>",
1047
+ "<extra_id_90>",
1048
+ "<extra_id_91>",
1049
+ "<extra_id_92>",
1050
+ "<extra_id_93>",
1051
+ "<extra_id_94>",
1052
+ "<extra_id_95>",
1053
+ "<extra_id_96>",
1054
+ "<extra_id_97>",
1055
+ "<extra_id_98>",
1056
+ "<extra_id_99>",
1057
+ "<extra_id_100>",
1058
+ "<extra_id_101>",
1059
+ "<extra_id_102>",
1060
+ "<extra_id_103>",
1061
+ "<extra_id_104>",
1062
+ "<extra_id_105>",
1063
+ "<extra_id_106>",
1064
+ "<extra_id_107>",
1065
+ "<extra_id_108>",
1066
+ "<extra_id_109>",
1067
+ "<extra_id_110>",
1068
+ "<extra_id_111>",
1069
+ "<extra_id_112>",
1070
+ "<extra_id_113>",
1071
+ "<extra_id_114>",
1072
+ "<extra_id_115>"
1073
+ ],
1074
+ "clean_up_tokenization_spaces": true,
1075
+ "eos_token": "</s>",
1076
+ "extra_ids": 116,
1077
+ "mask_token": "<extra_id_0>",
1078
+ "model_max_length": 1000000000000000019884624838656,
1079
+ "pad_token": "<pad>",
1080
+ "tokenizer_class": "T5Tokenizer",
1081
+ "unk_token": "<unk>"
1082
+ }