pszemraj commited on
Commit
dcf63ab
1 Parent(s): fb1e556

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +105 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +135 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +981 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 65001,
3
+ "<extra_id_0>": 65003,
4
+ "<extra_id_10>": 65013,
5
+ "<extra_id_11>": 65014,
6
+ "<extra_id_12>": 65015,
7
+ "<extra_id_13>": 65016,
8
+ "<extra_id_14>": 65017,
9
+ "<extra_id_15>": 65018,
10
+ "<extra_id_16>": 65019,
11
+ "<extra_id_17>": 65020,
12
+ "<extra_id_18>": 65021,
13
+ "<extra_id_19>": 65022,
14
+ "<extra_id_1>": 65004,
15
+ "<extra_id_20>": 65023,
16
+ "<extra_id_21>": 65024,
17
+ "<extra_id_22>": 65025,
18
+ "<extra_id_23>": 65026,
19
+ "<extra_id_24>": 65027,
20
+ "<extra_id_25>": 65028,
21
+ "<extra_id_26>": 65029,
22
+ "<extra_id_27>": 65030,
23
+ "<extra_id_28>": 65031,
24
+ "<extra_id_29>": 65032,
25
+ "<extra_id_2>": 65005,
26
+ "<extra_id_30>": 65033,
27
+ "<extra_id_31>": 65034,
28
+ "<extra_id_32>": 65035,
29
+ "<extra_id_33>": 65036,
30
+ "<extra_id_34>": 65037,
31
+ "<extra_id_35>": 65038,
32
+ "<extra_id_36>": 65039,
33
+ "<extra_id_37>": 65040,
34
+ "<extra_id_38>": 65041,
35
+ "<extra_id_39>": 65042,
36
+ "<extra_id_3>": 65006,
37
+ "<extra_id_40>": 65043,
38
+ "<extra_id_41>": 65044,
39
+ "<extra_id_42>": 65045,
40
+ "<extra_id_43>": 65046,
41
+ "<extra_id_44>": 65047,
42
+ "<extra_id_45>": 65048,
43
+ "<extra_id_46>": 65049,
44
+ "<extra_id_47>": 65050,
45
+ "<extra_id_48>": 65051,
46
+ "<extra_id_49>": 65052,
47
+ "<extra_id_4>": 65007,
48
+ "<extra_id_50>": 65053,
49
+ "<extra_id_51>": 65054,
50
+ "<extra_id_52>": 65055,
51
+ "<extra_id_53>": 65056,
52
+ "<extra_id_54>": 65057,
53
+ "<extra_id_55>": 65058,
54
+ "<extra_id_56>": 65059,
55
+ "<extra_id_57>": 65060,
56
+ "<extra_id_58>": 65061,
57
+ "<extra_id_59>": 65062,
58
+ "<extra_id_5>": 65008,
59
+ "<extra_id_60>": 65063,
60
+ "<extra_id_61>": 65064,
61
+ "<extra_id_62>": 65065,
62
+ "<extra_id_63>": 65066,
63
+ "<extra_id_64>": 65067,
64
+ "<extra_id_65>": 65068,
65
+ "<extra_id_66>": 65069,
66
+ "<extra_id_67>": 65070,
67
+ "<extra_id_68>": 65071,
68
+ "<extra_id_69>": 65072,
69
+ "<extra_id_6>": 65009,
70
+ "<extra_id_70>": 65073,
71
+ "<extra_id_71>": 65074,
72
+ "<extra_id_72>": 65075,
73
+ "<extra_id_73>": 65076,
74
+ "<extra_id_74>": 65077,
75
+ "<extra_id_75>": 65078,
76
+ "<extra_id_76>": 65079,
77
+ "<extra_id_77>": 65080,
78
+ "<extra_id_78>": 65081,
79
+ "<extra_id_79>": 65082,
80
+ "<extra_id_7>": 65010,
81
+ "<extra_id_80>": 65083,
82
+ "<extra_id_81>": 65084,
83
+ "<extra_id_82>": 65085,
84
+ "<extra_id_83>": 65086,
85
+ "<extra_id_84>": 65087,
86
+ "<extra_id_85>": 65088,
87
+ "<extra_id_86>": 65089,
88
+ "<extra_id_87>": 65090,
89
+ "<extra_id_88>": 65091,
90
+ "<extra_id_89>": 65092,
91
+ "<extra_id_8>": 65011,
92
+ "<extra_id_90>": 65093,
93
+ "<extra_id_91>": 65094,
94
+ "<extra_id_92>": 65095,
95
+ "<extra_id_93>": 65096,
96
+ "<extra_id_94>": 65097,
97
+ "<extra_id_95>": 65098,
98
+ "<extra_id_96>": 65099,
99
+ "<extra_id_97>": 65100,
100
+ "<extra_id_98>": 65101,
101
+ "<extra_id_99>": 65102,
102
+ "<extra_id_9>": 65012,
103
+ "<pad>": 65000,
104
+ "<unk>": 65002
105
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,135 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<pad>",
4
+ "</s>",
5
+ "<unk>",
6
+ "<extra_id_0>",
7
+ "<extra_id_1>",
8
+ "<extra_id_2>",
9
+ "<extra_id_3>",
10
+ "<extra_id_4>",
11
+ "<extra_id_5>",
12
+ "<extra_id_6>",
13
+ "<extra_id_7>",
14
+ "<extra_id_8>",
15
+ "<extra_id_9>",
16
+ "<extra_id_10>",
17
+ "<extra_id_11>",
18
+ "<extra_id_12>",
19
+ "<extra_id_13>",
20
+ "<extra_id_14>",
21
+ "<extra_id_15>",
22
+ "<extra_id_16>",
23
+ "<extra_id_17>",
24
+ "<extra_id_18>",
25
+ "<extra_id_19>",
26
+ "<extra_id_20>",
27
+ "<extra_id_21>",
28
+ "<extra_id_22>",
29
+ "<extra_id_23>",
30
+ "<extra_id_24>",
31
+ "<extra_id_25>",
32
+ "<extra_id_26>",
33
+ "<extra_id_27>",
34
+ "<extra_id_28>",
35
+ "<extra_id_29>",
36
+ "<extra_id_30>",
37
+ "<extra_id_31>",
38
+ "<extra_id_32>",
39
+ "<extra_id_33>",
40
+ "<extra_id_34>",
41
+ "<extra_id_35>",
42
+ "<extra_id_36>",
43
+ "<extra_id_37>",
44
+ "<extra_id_38>",
45
+ "<extra_id_39>",
46
+ "<extra_id_40>",
47
+ "<extra_id_41>",
48
+ "<extra_id_42>",
49
+ "<extra_id_43>",
50
+ "<extra_id_44>",
51
+ "<extra_id_45>",
52
+ "<extra_id_46>",
53
+ "<extra_id_47>",
54
+ "<extra_id_48>",
55
+ "<extra_id_49>",
56
+ "<extra_id_50>",
57
+ "<extra_id_51>",
58
+ "<extra_id_52>",
59
+ "<extra_id_53>",
60
+ "<extra_id_54>",
61
+ "<extra_id_55>",
62
+ "<extra_id_56>",
63
+ "<extra_id_57>",
64
+ "<extra_id_58>",
65
+ "<extra_id_59>",
66
+ "<extra_id_60>",
67
+ "<extra_id_61>",
68
+ "<extra_id_62>",
69
+ "<extra_id_63>",
70
+ "<extra_id_64>",
71
+ "<extra_id_65>",
72
+ "<extra_id_66>",
73
+ "<extra_id_67>",
74
+ "<extra_id_68>",
75
+ "<extra_id_69>",
76
+ "<extra_id_70>",
77
+ "<extra_id_71>",
78
+ "<extra_id_72>",
79
+ "<extra_id_73>",
80
+ "<extra_id_74>",
81
+ "<extra_id_75>",
82
+ "<extra_id_76>",
83
+ "<extra_id_77>",
84
+ "<extra_id_78>",
85
+ "<extra_id_79>",
86
+ "<extra_id_80>",
87
+ "<extra_id_81>",
88
+ "<extra_id_82>",
89
+ "<extra_id_83>",
90
+ "<extra_id_84>",
91
+ "<extra_id_85>",
92
+ "<extra_id_86>",
93
+ "<extra_id_87>",
94
+ "<extra_id_88>",
95
+ "<extra_id_89>",
96
+ "<extra_id_90>",
97
+ "<extra_id_91>",
98
+ "<extra_id_92>",
99
+ "<extra_id_93>",
100
+ "<extra_id_94>",
101
+ "<extra_id_95>",
102
+ "<extra_id_96>",
103
+ "<extra_id_97>",
104
+ "<extra_id_98>",
105
+ "<extra_id_99>"
106
+ ],
107
+ "bos_token": {
108
+ "content": "<EOT>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false
113
+ },
114
+ "eos_token": {
115
+ "content": "</s>",
116
+ "lstrip": false,
117
+ "normalized": false,
118
+ "rstrip": false,
119
+ "single_word": false
120
+ },
121
+ "pad_token": {
122
+ "content": "<pad>",
123
+ "lstrip": false,
124
+ "normalized": false,
125
+ "rstrip": false,
126
+ "single_word": false
127
+ },
128
+ "unk_token": {
129
+ "content": "<unk>",
130
+ "lstrip": false,
131
+ "normalized": false,
132
+ "rstrip": false,
133
+ "single_word": false
134
+ }
135
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,981 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<EOT>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<META>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<META_START>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<META_END>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<SOS>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "65000": {
45
+ "content": "<pad>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "65001": {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "65002": {
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "65003": {
69
+ "content": "<extra_id_0>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "65004": {
77
+ "content": "<extra_id_1>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "65005": {
85
+ "content": "<extra_id_2>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "65006": {
93
+ "content": "<extra_id_3>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "65007": {
101
+ "content": "<extra_id_4>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "65008": {
109
+ "content": "<extra_id_5>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "65009": {
117
+ "content": "<extra_id_6>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "65010": {
125
+ "content": "<extra_id_7>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "65011": {
133
+ "content": "<extra_id_8>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "65012": {
141
+ "content": "<extra_id_9>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "65013": {
149
+ "content": "<extra_id_10>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "65014": {
157
+ "content": "<extra_id_11>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "65015": {
165
+ "content": "<extra_id_12>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "65016": {
173
+ "content": "<extra_id_13>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "65017": {
181
+ "content": "<extra_id_14>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "65018": {
189
+ "content": "<extra_id_15>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "65019": {
197
+ "content": "<extra_id_16>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "65020": {
205
+ "content": "<extra_id_17>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "65021": {
213
+ "content": "<extra_id_18>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "65022": {
221
+ "content": "<extra_id_19>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "65023": {
229
+ "content": "<extra_id_20>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "65024": {
237
+ "content": "<extra_id_21>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "65025": {
245
+ "content": "<extra_id_22>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "65026": {
253
+ "content": "<extra_id_23>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "65027": {
261
+ "content": "<extra_id_24>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "65028": {
269
+ "content": "<extra_id_25>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "65029": {
277
+ "content": "<extra_id_26>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "65030": {
285
+ "content": "<extra_id_27>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "65031": {
293
+ "content": "<extra_id_28>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "65032": {
301
+ "content": "<extra_id_29>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "65033": {
309
+ "content": "<extra_id_30>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "65034": {
317
+ "content": "<extra_id_31>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "65035": {
325
+ "content": "<extra_id_32>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "65036": {
333
+ "content": "<extra_id_33>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "65037": {
341
+ "content": "<extra_id_34>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "65038": {
349
+ "content": "<extra_id_35>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "65039": {
357
+ "content": "<extra_id_36>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "65040": {
365
+ "content": "<extra_id_37>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "65041": {
373
+ "content": "<extra_id_38>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "65042": {
381
+ "content": "<extra_id_39>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "65043": {
389
+ "content": "<extra_id_40>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "65044": {
397
+ "content": "<extra_id_41>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "65045": {
405
+ "content": "<extra_id_42>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "65046": {
413
+ "content": "<extra_id_43>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "65047": {
421
+ "content": "<extra_id_44>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "65048": {
429
+ "content": "<extra_id_45>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "65049": {
437
+ "content": "<extra_id_46>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "65050": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "65051": {
453
+ "content": "<extra_id_48>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "65052": {
461
+ "content": "<extra_id_49>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "65053": {
469
+ "content": "<extra_id_50>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "65054": {
477
+ "content": "<extra_id_51>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "65055": {
485
+ "content": "<extra_id_52>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "65056": {
493
+ "content": "<extra_id_53>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "65057": {
501
+ "content": "<extra_id_54>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "65058": {
509
+ "content": "<extra_id_55>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "65059": {
517
+ "content": "<extra_id_56>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "65060": {
525
+ "content": "<extra_id_57>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "65061": {
533
+ "content": "<extra_id_58>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "65062": {
541
+ "content": "<extra_id_59>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "65063": {
549
+ "content": "<extra_id_60>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "65064": {
557
+ "content": "<extra_id_61>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "65065": {
565
+ "content": "<extra_id_62>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "65066": {
573
+ "content": "<extra_id_63>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "65067": {
581
+ "content": "<extra_id_64>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "65068": {
589
+ "content": "<extra_id_65>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "65069": {
597
+ "content": "<extra_id_66>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "65070": {
605
+ "content": "<extra_id_67>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "65071": {
613
+ "content": "<extra_id_68>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "65072": {
621
+ "content": "<extra_id_69>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "65073": {
629
+ "content": "<extra_id_70>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "65074": {
637
+ "content": "<extra_id_71>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "65075": {
645
+ "content": "<extra_id_72>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "65076": {
653
+ "content": "<extra_id_73>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "65077": {
661
+ "content": "<extra_id_74>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "65078": {
669
+ "content": "<extra_id_75>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "65079": {
677
+ "content": "<extra_id_76>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "65080": {
685
+ "content": "<extra_id_77>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "65081": {
693
+ "content": "<extra_id_78>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "65082": {
701
+ "content": "<extra_id_79>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "65083": {
709
+ "content": "<extra_id_80>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "65084": {
717
+ "content": "<extra_id_81>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "65085": {
725
+ "content": "<extra_id_82>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "65086": {
733
+ "content": "<extra_id_83>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "65087": {
741
+ "content": "<extra_id_84>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "65088": {
749
+ "content": "<extra_id_85>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "65089": {
757
+ "content": "<extra_id_86>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "65090": {
765
+ "content": "<extra_id_87>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "65091": {
773
+ "content": "<extra_id_88>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "65092": {
781
+ "content": "<extra_id_89>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "65093": {
789
+ "content": "<extra_id_90>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "65094": {
797
+ "content": "<extra_id_91>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "65095": {
805
+ "content": "<extra_id_92>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "65096": {
813
+ "content": "<extra_id_93>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "65097": {
821
+ "content": "<extra_id_94>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "65098": {
829
+ "content": "<extra_id_95>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "65099": {
837
+ "content": "<extra_id_96>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "65100": {
845
+ "content": "<extra_id_97>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "65101": {
853
+ "content": "<extra_id_98>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "65102": {
861
+ "content": "<extra_id_99>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ }
868
+ },
869
+ "additional_special_tokens": [
870
+ "<pad>",
871
+ "</s>",
872
+ "<unk>",
873
+ "<extra_id_0>",
874
+ "<extra_id_1>",
875
+ "<extra_id_2>",
876
+ "<extra_id_3>",
877
+ "<extra_id_4>",
878
+ "<extra_id_5>",
879
+ "<extra_id_6>",
880
+ "<extra_id_7>",
881
+ "<extra_id_8>",
882
+ "<extra_id_9>",
883
+ "<extra_id_10>",
884
+ "<extra_id_11>",
885
+ "<extra_id_12>",
886
+ "<extra_id_13>",
887
+ "<extra_id_14>",
888
+ "<extra_id_15>",
889
+ "<extra_id_16>",
890
+ "<extra_id_17>",
891
+ "<extra_id_18>",
892
+ "<extra_id_19>",
893
+ "<extra_id_20>",
894
+ "<extra_id_21>",
895
+ "<extra_id_22>",
896
+ "<extra_id_23>",
897
+ "<extra_id_24>",
898
+ "<extra_id_25>",
899
+ "<extra_id_26>",
900
+ "<extra_id_27>",
901
+ "<extra_id_28>",
902
+ "<extra_id_29>",
903
+ "<extra_id_30>",
904
+ "<extra_id_31>",
905
+ "<extra_id_32>",
906
+ "<extra_id_33>",
907
+ "<extra_id_34>",
908
+ "<extra_id_35>",
909
+ "<extra_id_36>",
910
+ "<extra_id_37>",
911
+ "<extra_id_38>",
912
+ "<extra_id_39>",
913
+ "<extra_id_40>",
914
+ "<extra_id_41>",
915
+ "<extra_id_42>",
916
+ "<extra_id_43>",
917
+ "<extra_id_44>",
918
+ "<extra_id_45>",
919
+ "<extra_id_46>",
920
+ "<extra_id_47>",
921
+ "<extra_id_48>",
922
+ "<extra_id_49>",
923
+ "<extra_id_50>",
924
+ "<extra_id_51>",
925
+ "<extra_id_52>",
926
+ "<extra_id_53>",
927
+ "<extra_id_54>",
928
+ "<extra_id_55>",
929
+ "<extra_id_56>",
930
+ "<extra_id_57>",
931
+ "<extra_id_58>",
932
+ "<extra_id_59>",
933
+ "<extra_id_60>",
934
+ "<extra_id_61>",
935
+ "<extra_id_62>",
936
+ "<extra_id_63>",
937
+ "<extra_id_64>",
938
+ "<extra_id_65>",
939
+ "<extra_id_66>",
940
+ "<extra_id_67>",
941
+ "<extra_id_68>",
942
+ "<extra_id_69>",
943
+ "<extra_id_70>",
944
+ "<extra_id_71>",
945
+ "<extra_id_72>",
946
+ "<extra_id_73>",
947
+ "<extra_id_74>",
948
+ "<extra_id_75>",
949
+ "<extra_id_76>",
950
+ "<extra_id_77>",
951
+ "<extra_id_78>",
952
+ "<extra_id_79>",
953
+ "<extra_id_80>",
954
+ "<extra_id_81>",
955
+ "<extra_id_82>",
956
+ "<extra_id_83>",
957
+ "<extra_id_84>",
958
+ "<extra_id_85>",
959
+ "<extra_id_86>",
960
+ "<extra_id_87>",
961
+ "<extra_id_88>",
962
+ "<extra_id_89>",
963
+ "<extra_id_90>",
964
+ "<extra_id_91>",
965
+ "<extra_id_92>",
966
+ "<extra_id_93>",
967
+ "<extra_id_94>",
968
+ "<extra_id_95>",
969
+ "<extra_id_96>",
970
+ "<extra_id_97>",
971
+ "<extra_id_98>",
972
+ "<extra_id_99>"
973
+ ],
974
+ "bos_token": "<EOT>",
975
+ "clean_up_tokenization_spaces": true,
976
+ "eos_token": "</s>",
977
+ "model_max_length": 1000000000,
978
+ "pad_token": "<pad>",
979
+ "tokenizer_class": "GPT2Tokenizer",
980
+ "unk_token": "<unk>"
981
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff