AlekseyKorshuk commited on
Commit
04c8c3f
1 Parent(s): da41ee0

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +145 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +1167 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|extratoken_100|>": 50356,
3
+ "<|extratoken_101|>": 50357,
4
+ "<|extratoken_102|>": 50358,
5
+ "<|extratoken_103|>": 50359,
6
+ "<|extratoken_104|>": 50360,
7
+ "<|extratoken_105|>": 50361,
8
+ "<|extratoken_106|>": 50362,
9
+ "<|extratoken_107|>": 50363,
10
+ "<|extratoken_108|>": 50364,
11
+ "<|extratoken_109|>": 50365,
12
+ "<|extratoken_10|>": 50266,
13
+ "<|extratoken_110|>": 50366,
14
+ "<|extratoken_111|>": 50367,
15
+ "<|extratoken_112|>": 50368,
16
+ "<|extratoken_113|>": 50369,
17
+ "<|extratoken_114|>": 50370,
18
+ "<|extratoken_115|>": 50371,
19
+ "<|extratoken_116|>": 50372,
20
+ "<|extratoken_117|>": 50373,
21
+ "<|extratoken_118|>": 50374,
22
+ "<|extratoken_119|>": 50375,
23
+ "<|extratoken_11|>": 50267,
24
+ "<|extratoken_120|>": 50376,
25
+ "<|extratoken_121|>": 50377,
26
+ "<|extratoken_122|>": 50378,
27
+ "<|extratoken_123|>": 50379,
28
+ "<|extratoken_124|>": 50380,
29
+ "<|extratoken_125|>": 50381,
30
+ "<|extratoken_126|>": 50382,
31
+ "<|extratoken_127|>": 50383,
32
+ "<|extratoken_128|>": 50384,
33
+ "<|extratoken_129|>": 50385,
34
+ "<|extratoken_12|>": 50268,
35
+ "<|extratoken_130|>": 50386,
36
+ "<|extratoken_131|>": 50387,
37
+ "<|extratoken_132|>": 50388,
38
+ "<|extratoken_133|>": 50389,
39
+ "<|extratoken_134|>": 50390,
40
+ "<|extratoken_135|>": 50391,
41
+ "<|extratoken_136|>": 50392,
42
+ "<|extratoken_137|>": 50393,
43
+ "<|extratoken_138|>": 50394,
44
+ "<|extratoken_139|>": 50395,
45
+ "<|extratoken_13|>": 50269,
46
+ "<|extratoken_140|>": 50396,
47
+ "<|extratoken_141|>": 50397,
48
+ "<|extratoken_142|>": 50398,
49
+ "<|extratoken_143|>": 50399,
50
+ "<|extratoken_14|>": 50270,
51
+ "<|extratoken_15|>": 50271,
52
+ "<|extratoken_16|>": 50272,
53
+ "<|extratoken_17|>": 50273,
54
+ "<|extratoken_18|>": 50274,
55
+ "<|extratoken_19|>": 50275,
56
+ "<|extratoken_1|>": 50257,
57
+ "<|extratoken_20|>": 50276,
58
+ "<|extratoken_21|>": 50277,
59
+ "<|extratoken_22|>": 50278,
60
+ "<|extratoken_23|>": 50279,
61
+ "<|extratoken_24|>": 50280,
62
+ "<|extratoken_25|>": 50281,
63
+ "<|extratoken_26|>": 50282,
64
+ "<|extratoken_27|>": 50283,
65
+ "<|extratoken_28|>": 50284,
66
+ "<|extratoken_29|>": 50285,
67
+ "<|extratoken_2|>": 50258,
68
+ "<|extratoken_30|>": 50286,
69
+ "<|extratoken_31|>": 50287,
70
+ "<|extratoken_32|>": 50288,
71
+ "<|extratoken_33|>": 50289,
72
+ "<|extratoken_34|>": 50290,
73
+ "<|extratoken_35|>": 50291,
74
+ "<|extratoken_36|>": 50292,
75
+ "<|extratoken_37|>": 50293,
76
+ "<|extratoken_38|>": 50294,
77
+ "<|extratoken_39|>": 50295,
78
+ "<|extratoken_3|>": 50259,
79
+ "<|extratoken_40|>": 50296,
80
+ "<|extratoken_41|>": 50297,
81
+ "<|extratoken_42|>": 50298,
82
+ "<|extratoken_43|>": 50299,
83
+ "<|extratoken_44|>": 50300,
84
+ "<|extratoken_45|>": 50301,
85
+ "<|extratoken_46|>": 50302,
86
+ "<|extratoken_47|>": 50303,
87
+ "<|extratoken_48|>": 50304,
88
+ "<|extratoken_49|>": 50305,
89
+ "<|extratoken_4|>": 50260,
90
+ "<|extratoken_50|>": 50306,
91
+ "<|extratoken_51|>": 50307,
92
+ "<|extratoken_52|>": 50308,
93
+ "<|extratoken_53|>": 50309,
94
+ "<|extratoken_54|>": 50310,
95
+ "<|extratoken_55|>": 50311,
96
+ "<|extratoken_56|>": 50312,
97
+ "<|extratoken_57|>": 50313,
98
+ "<|extratoken_58|>": 50314,
99
+ "<|extratoken_59|>": 50315,
100
+ "<|extratoken_5|>": 50261,
101
+ "<|extratoken_60|>": 50316,
102
+ "<|extratoken_61|>": 50317,
103
+ "<|extratoken_62|>": 50318,
104
+ "<|extratoken_63|>": 50319,
105
+ "<|extratoken_64|>": 50320,
106
+ "<|extratoken_65|>": 50321,
107
+ "<|extratoken_66|>": 50322,
108
+ "<|extratoken_67|>": 50323,
109
+ "<|extratoken_68|>": 50324,
110
+ "<|extratoken_69|>": 50325,
111
+ "<|extratoken_6|>": 50262,
112
+ "<|extratoken_70|>": 50326,
113
+ "<|extratoken_71|>": 50327,
114
+ "<|extratoken_72|>": 50328,
115
+ "<|extratoken_73|>": 50329,
116
+ "<|extratoken_74|>": 50330,
117
+ "<|extratoken_75|>": 50331,
118
+ "<|extratoken_76|>": 50332,
119
+ "<|extratoken_77|>": 50333,
120
+ "<|extratoken_78|>": 50334,
121
+ "<|extratoken_79|>": 50335,
122
+ "<|extratoken_7|>": 50263,
123
+ "<|extratoken_80|>": 50336,
124
+ "<|extratoken_81|>": 50337,
125
+ "<|extratoken_82|>": 50338,
126
+ "<|extratoken_83|>": 50339,
127
+ "<|extratoken_84|>": 50340,
128
+ "<|extratoken_85|>": 50341,
129
+ "<|extratoken_86|>": 50342,
130
+ "<|extratoken_87|>": 50343,
131
+ "<|extratoken_88|>": 50344,
132
+ "<|extratoken_89|>": 50345,
133
+ "<|extratoken_8|>": 50264,
134
+ "<|extratoken_90|>": 50346,
135
+ "<|extratoken_91|>": 50347,
136
+ "<|extratoken_92|>": 50348,
137
+ "<|extratoken_93|>": 50349,
138
+ "<|extratoken_94|>": 50350,
139
+ "<|extratoken_95|>": 50351,
140
+ "<|extratoken_96|>": 50352,
141
+ "<|extratoken_97|>": 50353,
142
+ "<|extratoken_98|>": 50354,
143
+ "<|extratoken_99|>": 50355,
144
+ "<|extratoken_9|>": 50265
145
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|extratoken_1|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": false
19
+ },
20
+ "50258": {
21
+ "content": "<|extratoken_2|>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50259": {
29
+ "content": "<|extratoken_3|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50260": {
37
+ "content": "<|extratoken_4|>",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": "<|extratoken_5|>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": "<|extratoken_6|>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": "<|extratoken_7|>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": "<|extratoken_8|>",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": "<|extratoken_9|>",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": "<|extratoken_10|>",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": "<|extratoken_11|>",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": "<|extratoken_12|>",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": "<|extratoken_13|>",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": "<|extratoken_14|>",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": "<|extratoken_15|>",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": "<|extratoken_16|>",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": "<|extratoken_17|>",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": "<|extratoken_18|>",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": "<|extratoken_19|>",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": "<|extratoken_20|>",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": "<|extratoken_21|>",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": "<|extratoken_22|>",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": "<|extratoken_23|>",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": "<|extratoken_24|>",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": "<|extratoken_25|>",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": "<|extratoken_26|>",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": "<|extratoken_27|>",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": "<|extratoken_28|>",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": "<|extratoken_29|>",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": "<|extratoken_30|>",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "<|extratoken_31|>",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "<|extratoken_32|>",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "<|extratoken_33|>",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "<|extratoken_34|>",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "<|extratoken_35|>",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "<|extratoken_36|>",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "<|extratoken_37|>",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "<|extratoken_38|>",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "50295": {
317
+ "content": "<|extratoken_39|>",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "50296": {
325
+ "content": "<|extratoken_40|>",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "50297": {
333
+ "content": "<|extratoken_41|>",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "50298": {
341
+ "content": "<|extratoken_42|>",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "50299": {
349
+ "content": "<|extratoken_43|>",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "50300": {
357
+ "content": "<|extratoken_44|>",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "50301": {
365
+ "content": "<|extratoken_45|>",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "50302": {
373
+ "content": "<|extratoken_46|>",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "50303": {
381
+ "content": "<|extratoken_47|>",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "50304": {
389
+ "content": "<|extratoken_48|>",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "50305": {
397
+ "content": "<|extratoken_49|>",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "50306": {
405
+ "content": "<|extratoken_50|>",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "50307": {
413
+ "content": "<|extratoken_51|>",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "50308": {
421
+ "content": "<|extratoken_52|>",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "50309": {
429
+ "content": "<|extratoken_53|>",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "50310": {
437
+ "content": "<|extratoken_54|>",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "50311": {
445
+ "content": "<|extratoken_55|>",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "50312": {
453
+ "content": "<|extratoken_56|>",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "50313": {
461
+ "content": "<|extratoken_57|>",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "50314": {
469
+ "content": "<|extratoken_58|>",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "50315": {
477
+ "content": "<|extratoken_59|>",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "50316": {
485
+ "content": "<|extratoken_60|>",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "50317": {
493
+ "content": "<|extratoken_61|>",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "50318": {
501
+ "content": "<|extratoken_62|>",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "50319": {
509
+ "content": "<|extratoken_63|>",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "50320": {
517
+ "content": "<|extratoken_64|>",
518
+ "lstrip": false,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "50321": {
525
+ "content": "<|extratoken_65|>",
526
+ "lstrip": false,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "50322": {
533
+ "content": "<|extratoken_66|>",
534
+ "lstrip": false,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "50323": {
541
+ "content": "<|extratoken_67|>",
542
+ "lstrip": false,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "50324": {
549
+ "content": "<|extratoken_68|>",
550
+ "lstrip": false,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "50325": {
557
+ "content": "<|extratoken_69|>",
558
+ "lstrip": false,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "50326": {
565
+ "content": "<|extratoken_70|>",
566
+ "lstrip": false,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "50327": {
573
+ "content": "<|extratoken_71|>",
574
+ "lstrip": false,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "50328": {
581
+ "content": "<|extratoken_72|>",
582
+ "lstrip": false,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "50329": {
589
+ "content": "<|extratoken_73|>",
590
+ "lstrip": false,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "50330": {
597
+ "content": "<|extratoken_74|>",
598
+ "lstrip": false,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "50331": {
605
+ "content": "<|extratoken_75|>",
606
+ "lstrip": false,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "50332": {
613
+ "content": "<|extratoken_76|>",
614
+ "lstrip": false,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "50333": {
621
+ "content": "<|extratoken_77|>",
622
+ "lstrip": false,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "50334": {
629
+ "content": "<|extratoken_78|>",
630
+ "lstrip": false,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "50335": {
637
+ "content": "<|extratoken_79|>",
638
+ "lstrip": false,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "50336": {
645
+ "content": "<|extratoken_80|>",
646
+ "lstrip": false,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "50337": {
653
+ "content": "<|extratoken_81|>",
654
+ "lstrip": false,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "50338": {
661
+ "content": "<|extratoken_82|>",
662
+ "lstrip": false,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "50339": {
669
+ "content": "<|extratoken_83|>",
670
+ "lstrip": false,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "50340": {
677
+ "content": "<|extratoken_84|>",
678
+ "lstrip": false,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "50341": {
685
+ "content": "<|extratoken_85|>",
686
+ "lstrip": false,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "50342": {
693
+ "content": "<|extratoken_86|>",
694
+ "lstrip": false,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "50343": {
701
+ "content": "<|extratoken_87|>",
702
+ "lstrip": false,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "50344": {
709
+ "content": "<|extratoken_88|>",
710
+ "lstrip": false,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "50345": {
717
+ "content": "<|extratoken_89|>",
718
+ "lstrip": false,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "50346": {
725
+ "content": "<|extratoken_90|>",
726
+ "lstrip": false,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "50347": {
733
+ "content": "<|extratoken_91|>",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "50348": {
741
+ "content": "<|extratoken_92|>",
742
+ "lstrip": false,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "50349": {
749
+ "content": "<|extratoken_93|>",
750
+ "lstrip": false,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "50350": {
757
+ "content": "<|extratoken_94|>",
758
+ "lstrip": false,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "50351": {
765
+ "content": "<|extratoken_95|>",
766
+ "lstrip": false,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "50352": {
773
+ "content": "<|extratoken_96|>",
774
+ "lstrip": false,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "50353": {
781
+ "content": "<|extratoken_97|>",
782
+ "lstrip": false,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "50354": {
789
+ "content": "<|extratoken_98|>",
790
+ "lstrip": false,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "50355": {
797
+ "content": "<|extratoken_99|>",
798
+ "lstrip": false,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "50356": {
805
+ "content": "<|extratoken_100|>",
806
+ "lstrip": false,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "50357": {
813
+ "content": "<|extratoken_101|>",
814
+ "lstrip": false,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "50358": {
821
+ "content": "<|extratoken_102|>",
822
+ "lstrip": false,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ },
828
+ "50359": {
829
+ "content": "<|extratoken_103|>",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "50360": {
837
+ "content": "<|extratoken_104|>",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "50361": {
845
+ "content": "<|extratoken_105|>",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "50362": {
853
+ "content": "<|extratoken_106|>",
854
+ "lstrip": false,
855
+ "normalized": true,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": false
859
+ },
860
+ "50363": {
861
+ "content": "<|extratoken_107|>",
862
+ "lstrip": false,
863
+ "normalized": true,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false
867
+ },
868
+ "50364": {
869
+ "content": "<|extratoken_108|>",
870
+ "lstrip": false,
871
+ "normalized": true,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "50365": {
877
+ "content": "<|extratoken_109|>",
878
+ "lstrip": false,
879
+ "normalized": true,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "50366": {
885
+ "content": "<|extratoken_110|>",
886
+ "lstrip": false,
887
+ "normalized": true,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "50367": {
893
+ "content": "<|extratoken_111|>",
894
+ "lstrip": false,
895
+ "normalized": true,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "50368": {
901
+ "content": "<|extratoken_112|>",
902
+ "lstrip": false,
903
+ "normalized": true,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "50369": {
909
+ "content": "<|extratoken_113|>",
910
+ "lstrip": false,
911
+ "normalized": true,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "50370": {
917
+ "content": "<|extratoken_114|>",
918
+ "lstrip": false,
919
+ "normalized": true,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "50371": {
925
+ "content": "<|extratoken_115|>",
926
+ "lstrip": false,
927
+ "normalized": true,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ },
932
+ "50372": {
933
+ "content": "<|extratoken_116|>",
934
+ "lstrip": false,
935
+ "normalized": true,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false
939
+ },
940
+ "50373": {
941
+ "content": "<|extratoken_117|>",
942
+ "lstrip": false,
943
+ "normalized": true,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": false
947
+ },
948
+ "50374": {
949
+ "content": "<|extratoken_118|>",
950
+ "lstrip": false,
951
+ "normalized": true,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": false
955
+ },
956
+ "50375": {
957
+ "content": "<|extratoken_119|>",
958
+ "lstrip": false,
959
+ "normalized": true,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": false
963
+ },
964
+ "50376": {
965
+ "content": "<|extratoken_120|>",
966
+ "lstrip": false,
967
+ "normalized": true,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": false
971
+ },
972
+ "50377": {
973
+ "content": "<|extratoken_121|>",
974
+ "lstrip": false,
975
+ "normalized": true,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": false
979
+ },
980
+ "50378": {
981
+ "content": "<|extratoken_122|>",
982
+ "lstrip": false,
983
+ "normalized": true,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": false
987
+ },
988
+ "50379": {
989
+ "content": "<|extratoken_123|>",
990
+ "lstrip": false,
991
+ "normalized": true,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": false
995
+ },
996
+ "50380": {
997
+ "content": "<|extratoken_124|>",
998
+ "lstrip": false,
999
+ "normalized": true,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": false
1003
+ },
1004
+ "50381": {
1005
+ "content": "<|extratoken_125|>",
1006
+ "lstrip": false,
1007
+ "normalized": true,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false
1011
+ },
1012
+ "50382": {
1013
+ "content": "<|extratoken_126|>",
1014
+ "lstrip": false,
1015
+ "normalized": true,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": false
1019
+ },
1020
+ "50383": {
1021
+ "content": "<|extratoken_127|>",
1022
+ "lstrip": false,
1023
+ "normalized": true,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": false
1027
+ },
1028
+ "50384": {
1029
+ "content": "<|extratoken_128|>",
1030
+ "lstrip": false,
1031
+ "normalized": true,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": false
1035
+ },
1036
+ "50385": {
1037
+ "content": "<|extratoken_129|>",
1038
+ "lstrip": false,
1039
+ "normalized": true,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": false
1043
+ },
1044
+ "50386": {
1045
+ "content": "<|extratoken_130|>",
1046
+ "lstrip": false,
1047
+ "normalized": true,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": false
1051
+ },
1052
+ "50387": {
1053
+ "content": "<|extratoken_131|>",
1054
+ "lstrip": false,
1055
+ "normalized": true,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": false
1059
+ },
1060
+ "50388": {
1061
+ "content": "<|extratoken_132|>",
1062
+ "lstrip": false,
1063
+ "normalized": true,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": false
1067
+ },
1068
+ "50389": {
1069
+ "content": "<|extratoken_133|>",
1070
+ "lstrip": false,
1071
+ "normalized": true,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": false
1075
+ },
1076
+ "50390": {
1077
+ "content": "<|extratoken_134|>",
1078
+ "lstrip": false,
1079
+ "normalized": true,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false
1083
+ },
1084
+ "50391": {
1085
+ "content": "<|extratoken_135|>",
1086
+ "lstrip": false,
1087
+ "normalized": true,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": false
1091
+ },
1092
+ "50392": {
1093
+ "content": "<|extratoken_136|>",
1094
+ "lstrip": false,
1095
+ "normalized": true,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": false
1099
+ },
1100
+ "50393": {
1101
+ "content": "<|extratoken_137|>",
1102
+ "lstrip": false,
1103
+ "normalized": true,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": false
1107
+ },
1108
+ "50394": {
1109
+ "content": "<|extratoken_138|>",
1110
+ "lstrip": false,
1111
+ "normalized": true,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": false
1115
+ },
1116
+ "50395": {
1117
+ "content": "<|extratoken_139|>",
1118
+ "lstrip": false,
1119
+ "normalized": true,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": false
1123
+ },
1124
+ "50396": {
1125
+ "content": "<|extratoken_140|>",
1126
+ "lstrip": false,
1127
+ "normalized": true,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": false
1131
+ },
1132
+ "50397": {
1133
+ "content": "<|extratoken_141|>",
1134
+ "lstrip": false,
1135
+ "normalized": true,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": false
1139
+ },
1140
+ "50398": {
1141
+ "content": "<|extratoken_142|>",
1142
+ "lstrip": false,
1143
+ "normalized": true,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": false
1147
+ },
1148
+ "50399": {
1149
+ "content": "<|extratoken_143|>",
1150
+ "lstrip": false,
1151
+ "normalized": true,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false
1155
+ }
1156
+ },
1157
+ "bos_token": "<|endoftext|>",
1158
+ "clean_up_tokenization_spaces": true,
1159
+ "eos_token": "<|endoftext|>",
1160
+ "errors": "replace",
1161
+ "model_max_length": 2048,
1162
+ "pad_token": "<|endoftext|>",
1163
+ "padding_side": "left",
1164
+ "tokenizer_class": "GPT2Tokenizer",
1165
+ "truncation_side": "left",
1166
+ "unk_token": "<|endoftext|>"
1167
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff