Hugging Face's logo

HeshamHaroon
/
Arabic_mistral_7b

Text Generation
Transformers
Safetensors
Arabic
unsloth
Inference Endpoints
Model card Files Community
HeshamHaroon commited on
Commit
f329478
•
1 Parent(s): daa9ccf

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +239 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1888 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|extra_0|>",
6
+ "<|extra_1|>",
7
+ "<|extra_2|>",
8
+ "<|extra_3|>",
9
+ "<|extra_4|>",
10
+ "<|extra_5|>",
11
+ "<|extra_6|>",
12
+ "<|extra_7|>",
13
+ "<|extra_8|>",
14
+ "<|extra_9|>",
15
+ "<|extra_10|>",
16
+ "<|extra_11|>",
17
+ "<|extra_12|>",
18
+ "<|extra_13|>",
19
+ "<|extra_14|>",
20
+ "<|extra_15|>",
21
+ "<|extra_16|>",
22
+ "<|extra_17|>",
23
+ "<|extra_18|>",
24
+ "<|extra_19|>",
25
+ "<|extra_20|>",
26
+ "<|extra_21|>",
27
+ "<|extra_22|>",
28
+ "<|extra_23|>",
29
+ "<|extra_24|>",
30
+ "<|extra_25|>",
31
+ "<|extra_26|>",
32
+ "<|extra_27|>",
33
+ "<|extra_28|>",
34
+ "<|extra_29|>",
35
+ "<|extra_30|>",
36
+ "<|extra_31|>",
37
+ "<|extra_32|>",
38
+ "<|extra_33|>",
39
+ "<|extra_34|>",
40
+ "<|extra_35|>",
41
+ "<|extra_36|>",
42
+ "<|extra_37|>",
43
+ "<|extra_38|>",
44
+ "<|extra_39|>",
45
+ "<|extra_40|>",
46
+ "<|extra_41|>",
47
+ "<|extra_42|>",
48
+ "<|extra_43|>",
49
+ "<|extra_44|>",
50
+ "<|extra_45|>",
51
+ "<|extra_46|>",
52
+ "<|extra_47|>",
53
+ "<|extra_48|>",
54
+ "<|extra_49|>",
55
+ "<|extra_50|>",
56
+ "<|extra_51|>",
57
+ "<|extra_52|>",
58
+ "<|extra_53|>",
59
+ "<|extra_54|>",
60
+ "<|extra_55|>",
61
+ "<|extra_56|>",
62
+ "<|extra_57|>",
63
+ "<|extra_58|>",
64
+ "<|extra_59|>",
65
+ "<|extra_60|>",
66
+ "<|extra_61|>",
67
+ "<|extra_62|>",
68
+ "<|extra_63|>",
69
+ "<|extra_64|>",
70
+ "<|extra_65|>",
71
+ "<|extra_66|>",
72
+ "<|extra_67|>",
73
+ "<|extra_68|>",
74
+ "<|extra_69|>",
75
+ "<|extra_70|>",
76
+ "<|extra_71|>",
77
+ "<|extra_72|>",
78
+ "<|extra_73|>",
79
+ "<|extra_74|>",
80
+ "<|extra_75|>",
81
+ "<|extra_76|>",
82
+ "<|extra_77|>",
83
+ "<|extra_78|>",
84
+ "<|extra_79|>",
85
+ "<|extra_80|>",
86
+ "<|extra_81|>",
87
+ "<|extra_82|>",
88
+ "<|extra_83|>",
89
+ "<|extra_84|>",
90
+ "<|extra_85|>",
91
+ "<|extra_86|>",
92
+ "<|extra_87|>",
93
+ "<|extra_88|>",
94
+ "<|extra_89|>",
95
+ "<|extra_90|>",
96
+ "<|extra_91|>",
97
+ "<|extra_92|>",
98
+ "<|extra_93|>",
99
+ "<|extra_94|>",
100
+ "<|extra_95|>",
101
+ "<|extra_96|>",
102
+ "<|extra_97|>",
103
+ "<|extra_98|>",
104
+ "<|extra_99|>",
105
+ "<|extra_100|>",
106
+ "<|extra_101|>",
107
+ "<|extra_102|>",
108
+ "<|extra_103|>",
109
+ "<|extra_104|>",
110
+ "<|extra_105|>",
111
+ "<|extra_106|>",
112
+ "<|extra_107|>",
113
+ "<|extra_108|>",
114
+ "<|extra_109|>",
115
+ "<|extra_110|>",
116
+ "<|extra_111|>",
117
+ "<|extra_112|>",
118
+ "<|extra_113|>",
119
+ "<|extra_114|>",
120
+ "<|extra_115|>",
121
+ "<|extra_116|>",
122
+ "<|extra_117|>",
123
+ "<|extra_118|>",
124
+ "<|extra_119|>",
125
+ "<|extra_120|>",
126
+ "<|extra_121|>",
127
+ "<|extra_122|>",
128
+ "<|extra_123|>",
129
+ "<|extra_124|>",
130
+ "<|extra_125|>",
131
+ "<|extra_126|>",
132
+ "<|extra_127|>",
133
+ "<|extra_128|>",
134
+ "<|extra_129|>",
135
+ "<|extra_130|>",
136
+ "<|extra_131|>",
137
+ "<|extra_132|>",
138
+ "<|extra_133|>",
139
+ "<|extra_134|>",
140
+ "<|extra_135|>",
141
+ "<|extra_136|>",
142
+ "<|extra_137|>",
143
+ "<|extra_138|>",
144
+ "<|extra_139|>",
145
+ "<|extra_140|>",
146
+ "<|extra_141|>",
147
+ "<|extra_142|>",
148
+ "<|extra_143|>",
149
+ "<|extra_144|>",
150
+ "<|extra_145|>",
151
+ "<|extra_146|>",
152
+ "<|extra_147|>",
153
+ "<|extra_148|>",
154
+ "<|extra_149|>",
155
+ "<|extra_150|>",
156
+ "<|extra_151|>",
157
+ "<|extra_152|>",
158
+ "<|extra_153|>",
159
+ "<|extra_154|>",
160
+ "<|extra_155|>",
161
+ "<|extra_156|>",
162
+ "<|extra_157|>",
163
+ "<|extra_158|>",
164
+ "<|extra_159|>",
165
+ "<|extra_160|>",
166
+ "<|extra_161|>",
167
+ "<|extra_162|>",
168
+ "<|extra_163|>",
169
+ "<|extra_164|>",
170
+ "<|extra_165|>",
171
+ "<|extra_166|>",
172
+ "<|extra_167|>",
173
+ "<|extra_168|>",
174
+ "<|extra_169|>",
175
+ "<|extra_170|>",
176
+ "<|extra_171|>",
177
+ "<|extra_172|>",
178
+ "<|extra_173|>",
179
+ "<|extra_174|>",
180
+ "<|extra_175|>",
181
+ "<|extra_176|>",
182
+ "<|extra_177|>",
183
+ "<|extra_178|>",
184
+ "<|extra_179|>",
185
+ "<|extra_180|>",
186
+ "<|extra_181|>",
187
+ "<|extra_182|>",
188
+ "<|extra_183|>",
189
+ "<|extra_184|>",
190
+ "<|extra_185|>",
191
+ "<|extra_186|>",
192
+ "<|extra_187|>",
193
+ "<|extra_188|>",
194
+ "<|extra_189|>",
195
+ "<|extra_190|>",
196
+ "<|extra_191|>",
197
+ "<|extra_192|>",
198
+ "<|extra_193|>",
199
+ "<|extra_194|>",
200
+ "<|extra_195|>",
201
+ "<|extra_196|>",
202
+ "<|extra_197|>",
203
+ "<|extra_198|>",
204
+ "<|extra_199|>",
205
+ "<|extra_200|>",
206
+ "<|extra_201|>",
207
+ "<|extra_202|>",
208
+ "<|extra_203|>",
209
+ "<|extra_204|>"
210
+ ],
211
+ "bos_token": {
212
+ "content": "<|endoftext|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false
217
+ },
218
+ "eos_token": {
219
+ "content": "<|endoftext|>",
220
+ "lstrip": false,
221
+ "normalized": false,
222
+ "rstrip": false,
223
+ "single_word": false
224
+ },
225
+ "pad_token": {
226
+ "content": "<|endoftext|>",
227
+ "lstrip": false,
228
+ "normalized": false,
229
+ "rstrip": false,
230
+ "single_word": false
231
+ },
232
+ "unk_token": {
233
+ "content": "<|endoftext|>",
234
+ "lstrip": false,
235
+ "normalized": false,
236
+ "rstrip": false,
237
+ "single_word": false
238
+ }
239
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,1888 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|extra_0|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|extra_1|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|extra_2|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|extra_3|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|extra_4|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|extra_5|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|extra_6|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|extra_7|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|extra_8|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|extra_9|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|extra_10|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<|extra_11|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "151658": {
126
+ "content": "<|extra_12|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "151659": {
134
+ "content": "<|extra_13|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "151660": {
142
+ "content": "<|extra_14|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "151661": {
150
+ "content": "<|extra_15|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "151662": {
158
+ "content": "<|extra_16|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "151663": {
166
+ "content": "<|extra_17|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "151664": {
174
+ "content": "<|extra_18|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "151665": {
182
+ "content": "<|extra_19|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|extra_20|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|extra_21|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<|extra_22|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<|extra_23|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|extra_24|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|extra_25|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|extra_26|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|extra_27|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|extra_28|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|extra_29|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<|extra_30|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<|extra_31|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<|extra_32|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<|extra_33|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<|extra_34|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<|extra_35|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<|extra_36|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<|extra_37|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<|extra_38|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<|extra_39|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<|extra_40|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<|extra_41|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<|extra_42|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<|extra_43|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<|extra_44|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<|extra_45|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<|extra_46|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<|extra_47|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<|extra_48|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<|extra_49|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<|extra_50|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<|extra_51|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<|extra_52|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<|extra_53|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<|extra_54|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<|extra_55|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<|extra_56|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<|extra_57|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<|extra_58|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<|extra_59|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<|extra_60|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<|extra_61|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<|extra_62|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<|extra_63|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<|extra_64|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<|extra_65|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<|extra_66|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<|extra_67|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<|extra_68|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<|extra_69|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<|extra_70|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<|extra_71|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<|extra_72|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<|extra_73|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<|extra_74|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<|extra_75|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<|extra_76|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<|extra_77|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<|extra_78|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<|extra_79|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<|extra_80|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<|extra_81|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<|extra_82|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<|extra_83|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<|extra_84|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<|extra_85|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<|extra_86|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<|extra_87|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<|extra_88|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<|extra_89|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<|extra_90|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<|extra_91|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<|extra_92|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<|extra_93|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<|extra_94|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<|extra_95|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<|extra_96|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<|extra_97|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<|extra_98|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<|extra_99|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<|extra_100|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<|extra_101|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<|extra_102|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<|extra_103|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<|extra_104|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<|extra_105|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "<|extra_106|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<|extra_107|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "<|extra_108|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<|extra_109|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<|extra_110|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "<|extra_111|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<|extra_112|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "<|extra_113|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<|extra_114|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<|extra_115|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<|extra_116|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<|extra_117|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<|extra_118|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<|extra_119|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<|extra_120|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<|extra_121|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<|extra_122|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<|extra_123|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<|extra_124|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<|extra_125|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<|extra_126|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<|extra_127|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<|extra_128|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<|extra_129|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<|extra_130|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<|extra_131|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<|extra_132|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<|extra_133|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<|extra_134|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<|extra_135|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<|extra_136|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<|extra_137|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<|extra_138|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<|extra_139|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<|extra_140|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<|extra_141|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<|extra_142|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<|extra_143|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<|extra_144|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<|extra_145|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<|extra_146|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<|extra_147|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<|extra_148|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<|extra_149|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<|extra_150|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<|extra_151|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<|extra_152|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<|extra_153|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<|extra_154|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<|extra_155|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<|extra_156|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<|extra_157|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<|extra_158|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<|extra_159|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<|extra_160|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<|extra_161|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<|extra_162|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<|extra_163|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<|extra_164|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<|extra_165|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<|extra_166|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<|extra_167|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<|extra_168|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<|extra_169|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<|extra_170|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<|extra_171|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<|extra_172|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "151819": {
1414
+ "content": "<|extra_173|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "151820": {
1422
+ "content": "<|extra_174|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "151821": {
1430
+ "content": "<|extra_175|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "151822": {
1438
+ "content": "<|extra_176|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "151823": {
1446
+ "content": "<|extra_177|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "151824": {
1454
+ "content": "<|extra_178|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "151825": {
1462
+ "content": "<|extra_179|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "151826": {
1470
+ "content": "<|extra_180|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "151827": {
1478
+ "content": "<|extra_181|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "151828": {
1486
+ "content": "<|extra_182|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "151829": {
1494
+ "content": "<|extra_183|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "151830": {
1502
+ "content": "<|extra_184|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "151831": {
1510
+ "content": "<|extra_185|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "151832": {
1518
+ "content": "<|extra_186|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "151833": {
1526
+ "content": "<|extra_187|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "151834": {
1534
+ "content": "<|extra_188|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "151835": {
1542
+ "content": "<|extra_189|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "151836": {
1550
+ "content": "<|extra_190|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "151837": {
1558
+ "content": "<|extra_191|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "151838": {
1566
+ "content": "<|extra_192|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "151839": {
1574
+ "content": "<|extra_193|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "151840": {
1582
+ "content": "<|extra_194|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "151841": {
1590
+ "content": "<|extra_195|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "151842": {
1598
+ "content": "<|extra_196|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "151843": {
1606
+ "content": "<|extra_197|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "151844": {
1614
+ "content": "<|extra_198|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "151845": {
1622
+ "content": "<|extra_199|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "151846": {
1630
+ "content": "<|extra_200|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "151847": {
1638
+ "content": "<|extra_201|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "151848": {
1646
+ "content": "<|extra_202|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "151849": {
1654
+ "content": "<|extra_203|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "151850": {
1662
+ "content": "<|extra_204|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ }
1669
+ },
1670
+ "additional_special_tokens": [
1671
+ "<|im_start|>",
1672
+ "<|im_end|>",
1673
+ "<|extra_0|>",
1674
+ "<|extra_1|>",
1675
+ "<|extra_2|>",
1676
+ "<|extra_3|>",
1677
+ "<|extra_4|>",
1678
+ "<|extra_5|>",
1679
+ "<|extra_6|>",
1680
+ "<|extra_7|>",
1681
+ "<|extra_8|>",
1682
+ "<|extra_9|>",
1683
+ "<|extra_10|>",
1684
+ "<|extra_11|>",
1685
+ "<|extra_12|>",
1686
+ "<|extra_13|>",
1687
+ "<|extra_14|>",
1688
+ "<|extra_15|>",
1689
+ "<|extra_16|>",
1690
+ "<|extra_17|>",
1691
+ "<|extra_18|>",
1692
+ "<|extra_19|>",
1693
+ "<|extra_20|>",
1694
+ "<|extra_21|>",
1695
+ "<|extra_22|>",
1696
+ "<|extra_23|>",
1697
+ "<|extra_24|>",
1698
+ "<|extra_25|>",
1699
+ "<|extra_26|>",
1700
+ "<|extra_27|>",
1701
+ "<|extra_28|>",
1702
+ "<|extra_29|>",
1703
+ "<|extra_30|>",
1704
+ "<|extra_31|>",
1705
+ "<|extra_32|>",
1706
+ "<|extra_33|>",
1707
+ "<|extra_34|>",
1708
+ "<|extra_35|>",
1709
+ "<|extra_36|>",
1710
+ "<|extra_37|>",
1711
+ "<|extra_38|>",
1712
+ "<|extra_39|>",
1713
+ "<|extra_40|>",
1714
+ "<|extra_41|>",
1715
+ "<|extra_42|>",
1716
+ "<|extra_43|>",
1717
+ "<|extra_44|>",
1718
+ "<|extra_45|>",
1719
+ "<|extra_46|>",
1720
+ "<|extra_47|>",
1721
+ "<|extra_48|>",
1722
+ "<|extra_49|>",
1723
+ "<|extra_50|>",
1724
+ "<|extra_51|>",
1725
+ "<|extra_52|>",
1726
+ "<|extra_53|>",
1727
+ "<|extra_54|>",
1728
+ "<|extra_55|>",
1729
+ "<|extra_56|>",
1730
+ "<|extra_57|>",
1731
+ "<|extra_58|>",
1732
+ "<|extra_59|>",
1733
+ "<|extra_60|>",
1734
+ "<|extra_61|>",
1735
+ "<|extra_62|>",
1736
+ "<|extra_63|>",
1737
+ "<|extra_64|>",
1738
+ "<|extra_65|>",
1739
+ "<|extra_66|>",
1740
+ "<|extra_67|>",
1741
+ "<|extra_68|>",
1742
+ "<|extra_69|>",
1743
+ "<|extra_70|>",
1744
+ "<|extra_71|>",
1745
+ "<|extra_72|>",
1746
+ "<|extra_73|>",
1747
+ "<|extra_74|>",
1748
+ "<|extra_75|>",
1749
+ "<|extra_76|>",
1750
+ "<|extra_77|>",
1751
+ "<|extra_78|>",
1752
+ "<|extra_79|>",
1753
+ "<|extra_80|>",
1754
+ "<|extra_81|>",
1755
+ "<|extra_82|>",
1756
+ "<|extra_83|>",
1757
+ "<|extra_84|>",
1758
+ "<|extra_85|>",
1759
+ "<|extra_86|>",
1760
+ "<|extra_87|>",
1761
+ "<|extra_88|>",
1762
+ "<|extra_89|>",
1763
+ "<|extra_90|>",
1764
+ "<|extra_91|>",
1765
+ "<|extra_92|>",
1766
+ "<|extra_93|>",
1767
+ "<|extra_94|>",
1768
+ "<|extra_95|>",
1769
+ "<|extra_96|>",
1770
+ "<|extra_97|>",
1771
+ "<|extra_98|>",
1772
+ "<|extra_99|>",
1773
+ "<|extra_100|>",
1774
+ "<|extra_101|>",
1775
+ "<|extra_102|>",
1776
+ "<|extra_103|>",
1777
+ "<|extra_104|>",
1778
+ "<|extra_105|>",
1779
+ "<|extra_106|>",
1780
+ "<|extra_107|>",
1781
+ "<|extra_108|>",
1782
+ "<|extra_109|>",
1783
+ "<|extra_110|>",
1784
+ "<|extra_111|>",
1785
+ "<|extra_112|>",
1786
+ "<|extra_113|>",
1787
+ "<|extra_114|>",
1788
+ "<|extra_115|>",
1789
+ "<|extra_116|>",
1790
+ "<|extra_117|>",
1791
+ "<|extra_118|>",
1792
+ "<|extra_119|>",
1793
+ "<|extra_120|>",
1794
+ "<|extra_121|>",
1795
+ "<|extra_122|>",
1796
+ "<|extra_123|>",
1797
+ "<|extra_124|>",
1798
+ "<|extra_125|>",
1799
+ "<|extra_126|>",
1800
+ "<|extra_127|>",
1801
+ "<|extra_128|>",
1802
+ "<|extra_129|>",
1803
+ "<|extra_130|>",
1804
+ "<|extra_131|>",
1805
+ "<|extra_132|>",
1806
+ "<|extra_133|>",
1807
+ "<|extra_134|>",
1808
+ "<|extra_135|>",
1809
+ "<|extra_136|>",
1810
+ "<|extra_137|>",
1811
+ "<|extra_138|>",
1812
+ "<|extra_139|>",
1813
+ "<|extra_140|>",
1814
+ "<|extra_141|>",
1815
+ "<|extra_142|>",
1816
+ "<|extra_143|>",
1817
+ "<|extra_144|>",
1818
+ "<|extra_145|>",
1819
+ "<|extra_146|>",
1820
+ "<|extra_147|>",
1821
+ "<|extra_148|>",
1822
+ "<|extra_149|>",
1823
+ "<|extra_150|>",
1824
+ "<|extra_151|>",
1825
+ "<|extra_152|>",
1826
+ "<|extra_153|>",
1827
+ "<|extra_154|>",
1828
+ "<|extra_155|>",
1829
+ "<|extra_156|>",
1830
+ "<|extra_157|>",
1831
+ "<|extra_158|>",
1832
+ "<|extra_159|>",
1833
+ "<|extra_160|>",
1834
+ "<|extra_161|>",
1835
+ "<|extra_162|>",
1836
+ "<|extra_163|>",
1837
+ "<|extra_164|>",
1838
+ "<|extra_165|>",
1839
+ "<|extra_166|>",
1840
+ "<|extra_167|>",
1841
+ "<|extra_168|>",
1842
+ "<|extra_169|>",
1843
+ "<|extra_170|>",
1844
+ "<|extra_171|>",
1845
+ "<|extra_172|>",
1846
+ "<|extra_173|>",
1847
+ "<|extra_174|>",
1848
+ "<|extra_175|>",
1849
+ "<|extra_176|>",
1850
+ "<|extra_177|>",
1851
+ "<|extra_178|>",
1852
+ "<|extra_179|>",
1853
+ "<|extra_180|>",
1854
+ "<|extra_181|>",
1855
+ "<|extra_182|>",
1856
+ "<|extra_183|>",
1857
+ "<|extra_184|>",
1858
+ "<|extra_185|>",
1859
+ "<|extra_186|>",
1860
+ "<|extra_187|>",
1861
+ "<|extra_188|>",
1862
+ "<|extra_189|>",
1863
+ "<|extra_190|>",
1864
+ "<|extra_191|>",
1865
+ "<|extra_192|>",
1866
+ "<|extra_193|>",
1867
+ "<|extra_194|>",
1868
+ "<|extra_195|>",
1869
+ "<|extra_196|>",
1870
+ "<|extra_197|>",
1871
+ "<|extra_198|>",
1872
+ "<|extra_199|>",
1873
+ "<|extra_200|>",
1874
+ "<|extra_201|>",
1875
+ "<|extra_202|>",
1876
+ "<|extra_203|>",
1877
+ "<|extra_204|>"
1878
+ ],
1879
+ "bos_token": "<|endoftext|>",
1880
+ "clean_up_tokenization_spaces": true,
1881
+ "eos_token": "<|endoftext|>",
1882
+ "errors": "replace",
1883
+ "model_max_length": 6144,
1884
+ "pad_token": "<|endoftext|>",
1885
+ "padding_side": "left",
1886
+ "tokenizer_class": "GPT2Tokenizer",
1887
+ "unk_token": "<|endoftext|>"
1888
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff