agemagician commited on
Commit
338514d
1 Parent(s): feb3c2d

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +124 -0
  2. tokenizer.json +1721 -0
  3. tokenizer_config.json +128 -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 +1,1721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
1139
+ "model": {
1140
+ "type": "Unigram",
1141
+ "unk_id": 2,
1142
+ "vocab": [
1143
+ [
1144
+ "<pad>",
1145
+ 0.0
1146
+ ],
1147
+ [
1148
+ "</s>",
1149
+ 0.0
1150
+ ],
1151
+ [
1152
+ "<unk>",
1153
+ 0.0
1154
+ ],
1155
+ [
1156
+ "A",
1157
+ -2.2783124446868896
1158
+ ],
1159
+ [
1160
+ "L",
1161
+ -2.3026247024536133
1162
+ ],
1163
+ [
1164
+ "G",
1165
+ -2.57137393951416
1166
+ ],
1167
+ [
1168
+ "V",
1169
+ -2.649644136428833
1170
+ ],
1171
+ [
1172
+ "S",
1173
+ -2.734614133834839
1174
+ ],
1175
+ [
1176
+ "R",
1177
+ -2.783693790435791
1178
+ ],
1179
+ [
1180
+ "E",
1181
+ -2.803671598434448
1182
+ ],
1183
+ [
1184
+ "D",
1185
+ -2.8803412914276123
1186
+ ],
1187
+ [
1188
+ "T",
1189
+ -2.903266429901123
1190
+ ],
1191
+ [
1192
+ "I",
1193
+ -2.9337375164031982
1194
+ ],
1195
+ [
1196
+ "P",
1197
+ -2.98986291885376
1198
+ ],
1199
+ [
1200
+ "K",
1201
+ -3.110422134399414
1202
+ ],
1203
+ [
1204
+ "F",
1205
+ -3.282776355743408
1206
+ ],
1207
+ [
1208
+ "Q",
1209
+ -3.3202931880950928
1210
+ ],
1211
+ [
1212
+ "N",
1213
+ -3.351658582687378
1214
+ ],
1215
+ [
1216
+ "Y",
1217
+ -3.605137825012207
1218
+ ],
1219
+ [
1220
+ "M",
1221
+ -3.781080961227417
1222
+ ],
1223
+ [
1224
+ "H",
1225
+ -3.8282647132873535
1226
+ ],
1227
+ [
1228
+ "W",
1229
+ -4.356028079986572
1230
+ ],
1231
+ [
1232
+ "C",
1233
+ -4.526663780212402
1234
+ ],
1235
+ [
1236
+ "X",
1237
+ -10.67774772644043
1238
+ ],
1239
+ [
1240
+ "B",
1241
+ -16.226823806762695
1242
+ ],
1243
+ [
1244
+ "O",
1245
+ -16.226823806762695
1246
+ ],
1247
+ [
1248
+ "U",
1249
+ -16.226823806762695
1250
+ ],
1251
+ [
1252
+ "Z",
1253
+ -16.226823806762695
1254
+ ],
1255
+ [
1256
+ "<extra_id_115>",
1257
+ 0.0
1258
+ ],
1259
+ [
1260
+ "<extra_id_114>",
1261
+ 0.0
1262
+ ],
1263
+ [
1264
+ "<extra_id_113>",
1265
+ 0.0
1266
+ ],
1267
+ [
1268
+ "<extra_id_112>",
1269
+ 0.0
1270
+ ],
1271
+ [
1272
+ "<extra_id_111>",
1273
+ 0.0
1274
+ ],
1275
+ [
1276
+ "<extra_id_110>",
1277
+ 0.0
1278
+ ],
1279
+ [
1280
+ "<extra_id_109>",
1281
+ 0.0
1282
+ ],
1283
+ [
1284
+ "<extra_id_108>",
1285
+ 0.0
1286
+ ],
1287
+ [
1288
+ "<extra_id_107>",
1289
+ 0.0
1290
+ ],
1291
+ [
1292
+ "<extra_id_106>",
1293
+ 0.0
1294
+ ],
1295
+ [
1296
+ "<extra_id_105>",
1297
+ 0.0
1298
+ ],
1299
+ [
1300
+ "<extra_id_104>",
1301
+ 0.0
1302
+ ],
1303
+ [
1304
+ "<extra_id_103>",
1305
+ 0.0
1306
+ ],
1307
+ [
1308
+ "<extra_id_102>",
1309
+ 0.0
1310
+ ],
1311
+ [
1312
+ "<extra_id_101>",
1313
+ 0.0
1314
+ ],
1315
+ [
1316
+ "<extra_id_100>",
1317
+ 0.0
1318
+ ],
1319
+ [
1320
+ "<extra_id_99>",
1321
+ 0.0
1322
+ ],
1323
+ [
1324
+ "<extra_id_98>",
1325
+ 0.0
1326
+ ],
1327
+ [
1328
+ "<extra_id_97>",
1329
+ 0.0
1330
+ ],
1331
+ [
1332
+ "<extra_id_96>",
1333
+ 0.0
1334
+ ],
1335
+ [
1336
+ "<extra_id_95>",
1337
+ 0.0
1338
+ ],
1339
+ [
1340
+ "<extra_id_94>",
1341
+ 0.0
1342
+ ],
1343
+ [
1344
+ "<extra_id_93>",
1345
+ 0.0
1346
+ ],
1347
+ [
1348
+ "<extra_id_92>",
1349
+ 0.0
1350
+ ],
1351
+ [
1352
+ "<extra_id_91>",
1353
+ 0.0
1354
+ ],
1355
+ [
1356
+ "<extra_id_90>",
1357
+ 0.0
1358
+ ],
1359
+ [
1360
+ "<extra_id_89>",
1361
+ 0.0
1362
+ ],
1363
+ [
1364
+ "<extra_id_88>",
1365
+ 0.0
1366
+ ],
1367
+ [
1368
+ "<extra_id_87>",
1369
+ 0.0
1370
+ ],
1371
+ [
1372
+ "<extra_id_86>",
1373
+ 0.0
1374
+ ],
1375
+ [
1376
+ "<extra_id_85>",
1377
+ 0.0
1378
+ ],
1379
+ [
1380
+ "<extra_id_84>",
1381
+ 0.0
1382
+ ],
1383
+ [
1384
+ "<extra_id_83>",
1385
+ 0.0
1386
+ ],
1387
+ [
1388
+ "<extra_id_82>",
1389
+ 0.0
1390
+ ],
1391
+ [
1392
+ "<extra_id_81>",
1393
+ 0.0
1394
+ ],
1395
+ [
1396
+ "<extra_id_80>",
1397
+ 0.0
1398
+ ],
1399
+ [
1400
+ "<extra_id_79>",
1401
+ 0.0
1402
+ ],
1403
+ [
1404
+ "<extra_id_78>",
1405
+ 0.0
1406
+ ],
1407
+ [
1408
+ "<extra_id_77>",
1409
+ 0.0
1410
+ ],
1411
+ [
1412
+ "<extra_id_76>",
1413
+ 0.0
1414
+ ],
1415
+ [
1416
+ "<extra_id_75>",
1417
+ 0.0
1418
+ ],
1419
+ [
1420
+ "<extra_id_74>",
1421
+ 0.0
1422
+ ],
1423
+ [
1424
+ "<extra_id_73>",
1425
+ 0.0
1426
+ ],
1427
+ [
1428
+ "<extra_id_72>",
1429
+ 0.0
1430
+ ],
1431
+ [
1432
+ "<extra_id_71>",
1433
+ 0.0
1434
+ ],
1435
+ [
1436
+ "<extra_id_70>",
1437
+ 0.0
1438
+ ],
1439
+ [
1440
+ "<extra_id_69>",
1441
+ 0.0
1442
+ ],
1443
+ [
1444
+ "<extra_id_68>",
1445
+ 0.0
1446
+ ],
1447
+ [
1448
+ "<extra_id_67>",
1449
+ 0.0
1450
+ ],
1451
+ [
1452
+ "<extra_id_66>",
1453
+ 0.0
1454
+ ],
1455
+ [
1456
+ "<extra_id_65>",
1457
+ 0.0
1458
+ ],
1459
+ [
1460
+ "<extra_id_64>",
1461
+ 0.0
1462
+ ],
1463
+ [
1464
+ "<extra_id_63>",
1465
+ 0.0
1466
+ ],
1467
+ [
1468
+ "<extra_id_62>",
1469
+ 0.0
1470
+ ],
1471
+ [
1472
+ "<extra_id_61>",
1473
+ 0.0
1474
+ ],
1475
+ [
1476
+ "<extra_id_60>",
1477
+ 0.0
1478
+ ],
1479
+ [
1480
+ "<extra_id_59>",
1481
+ 0.0
1482
+ ],
1483
+ [
1484
+ "<extra_id_58>",
1485
+ 0.0
1486
+ ],
1487
+ [
1488
+ "<extra_id_57>",
1489
+ 0.0
1490
+ ],
1491
+ [
1492
+ "<extra_id_56>",
1493
+ 0.0
1494
+ ],
1495
+ [
1496
+ "<extra_id_55>",
1497
+ 0.0
1498
+ ],
1499
+ [
1500
+ "<extra_id_54>",
1501
+ 0.0
1502
+ ],
1503
+ [
1504
+ "<extra_id_53>",
1505
+ 0.0
1506
+ ],
1507
+ [
1508
+ "<extra_id_52>",
1509
+ 0.0
1510
+ ],
1511
+ [
1512
+ "<extra_id_51>",
1513
+ 0.0
1514
+ ],
1515
+ [
1516
+ "<extra_id_50>",
1517
+ 0.0
1518
+ ],
1519
+ [
1520
+ "<extra_id_49>",
1521
+ 0.0
1522
+ ],
1523
+ [
1524
+ "<extra_id_48>",
1525
+ 0.0
1526
+ ],
1527
+ [
1528
+ "<extra_id_47>",
1529
+ 0.0
1530
+ ],
1531
+ [
1532
+ "<extra_id_46>",
1533
+ 0.0
1534
+ ],
1535
+ [
1536
+ "<extra_id_45>",
1537
+ 0.0
1538
+ ],
1539
+ [
1540
+ "<extra_id_44>",
1541
+ 0.0
1542
+ ],
1543
+ [
1544
+ "<extra_id_43>",
1545
+ 0.0
1546
+ ],
1547
+ [
1548
+ "<extra_id_42>",
1549
+ 0.0
1550
+ ],
1551
+ [
1552
+ "<extra_id_41>",
1553
+ 0.0
1554
+ ],
1555
+ [
1556
+ "<extra_id_40>",
1557
+ 0.0
1558
+ ],
1559
+ [
1560
+ "<extra_id_39>",
1561
+ 0.0
1562
+ ],
1563
+ [
1564
+ "<extra_id_38>",
1565
+ 0.0
1566
+ ],
1567
+ [
1568
+ "<extra_id_37>",
1569
+ 0.0
1570
+ ],
1571
+ [
1572
+ "<extra_id_36>",
1573
+ 0.0
1574
+ ],
1575
+ [
1576
+ "<extra_id_35>",
1577
+ 0.0
1578
+ ],
1579
+ [
1580
+ "<extra_id_34>",
1581
+ 0.0
1582
+ ],
1583
+ [
1584
+ "<extra_id_33>",
1585
+ 0.0
1586
+ ],
1587
+ [
1588
+ "<extra_id_32>",
1589
+ 0.0
1590
+ ],
1591
+ [
1592
+ "<extra_id_31>",
1593
+ 0.0
1594
+ ],
1595
+ [
1596
+ "<extra_id_30>",
1597
+ 0.0
1598
+ ],
1599
+ [
1600
+ "<extra_id_29>",
1601
+ 0.0
1602
+ ],
1603
+ [
1604
+ "<extra_id_28>",
1605
+ 0.0
1606
+ ],
1607
+ [
1608
+ "<extra_id_27>",
1609
+ 0.0
1610
+ ],
1611
+ [
1612
+ "<extra_id_26>",
1613
+ 0.0
1614
+ ],
1615
+ [
1616
+ "<extra_id_25>",
1617
+ 0.0
1618
+ ],
1619
+ [
1620
+ "<extra_id_24>",
1621
+ 0.0
1622
+ ],
1623
+ [
1624
+ "<extra_id_23>",
1625
+ 0.0
1626
+ ],
1627
+ [
1628
+ "<extra_id_22>",
1629
+ 0.0
1630
+ ],
1631
+ [
1632
+ "<extra_id_21>",
1633
+ 0.0
1634
+ ],
1635
+ [
1636
+ "<extra_id_20>",
1637
+ 0.0
1638
+ ],
1639
+ [
1640
+ "<extra_id_19>",
1641
+ 0.0
1642
+ ],
1643
+ [
1644
+ "<extra_id_18>",
1645
+ 0.0
1646
+ ],
1647
+ [
1648
+ "<extra_id_17>",
1649
+ 0.0
1650
+ ],
1651
+ [
1652
+ "<extra_id_16>",
1653
+ 0.0
1654
+ ],
1655
+ [
1656
+ "<extra_id_15>",
1657
+ 0.0
1658
+ ],
1659
+ [
1660
+ "<extra_id_14>",
1661
+ 0.0
1662
+ ],
1663
+ [
1664
+ "<extra_id_13>",
1665
+ 0.0
1666
+ ],
1667
+ [
1668
+ "<extra_id_12>",
1669
+ 0.0
1670
+ ],
1671
+ [
1672
+ "<extra_id_11>",
1673
+ 0.0
1674
+ ],
1675
+ [
1676
+ "<extra_id_10>",
1677
+ 0.0
1678
+ ],
1679
+ [
1680
+ "<extra_id_9>",
1681
+ 0.0
1682
+ ],
1683
+ [
1684
+ "<extra_id_8>",
1685
+ 0.0
1686
+ ],
1687
+ [
1688
+ "<extra_id_7>",
1689
+ 0.0
1690
+ ],
1691
+ [
1692
+ "<extra_id_6>",
1693
+ 0.0
1694
+ ],
1695
+ [
1696
+ "<extra_id_5>",
1697
+ 0.0
1698
+ ],
1699
+ [
1700
+ "<extra_id_4>",
1701
+ 0.0
1702
+ ],
1703
+ [
1704
+ "<extra_id_3>",
1705
+ 0.0
1706
+ ],
1707
+ [
1708
+ "<extra_id_2>",
1709
+ 0.0
1710
+ ],
1711
+ [
1712
+ "<extra_id_1>",
1713
+ 0.0
1714
+ ],
1715
+ [
1716
+ "<extra_id_0>",
1717
+ 0.0
1718
+ ]
1719
+ ]
1720
+ }
1721
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "extra_ids": 116,
122
+ "name_or_path": "agemagician/protx-large-1gspan-partreconstruction-20mlmp-encl48-decl24-ramd128-ranb64-dmodel1536-resume-17",
123
+ "pad_token": "<pad>",
124
+ "private": true,
125
+ "special_tokens_map_file": "tokenizer/protein_t5_fast_tokenizer_v4/special_tokens_map.json",
126
+ "tokenizer_class": "T5Tokenizer",
127
+ "unk_token": "<unk>"
128
+ }