XanderJC commited on
Commit
cc69e15
1 Parent(s): ae4188a

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