bjoernp commited on
Commit
1ef6e41
1 Parent(s): f8e7c01

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +127 -4
  2. special_tokens_map.json +35 -8
  3. tokenizer_config.json +1012 -8
added_tokens.json CHANGED
@@ -1,7 +1,130 @@
1
  {
2
- "</s>": 2,
3
- "<s>": 1,
4
- "<unk>": 0,
5
  "<|im_end|>": 32001,
6
- "<|im_start|>": 32000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
 
 
 
2
  "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000,
4
+ "<|padding_token_0|>": 32002,
5
+ "<|padding_token_100|>": 32102,
6
+ "<|padding_token_101|>": 32103,
7
+ "<|padding_token_102|>": 32104,
8
+ "<|padding_token_103|>": 32105,
9
+ "<|padding_token_104|>": 32106,
10
+ "<|padding_token_105|>": 32107,
11
+ "<|padding_token_106|>": 32108,
12
+ "<|padding_token_107|>": 32109,
13
+ "<|padding_token_108|>": 32110,
14
+ "<|padding_token_109|>": 32111,
15
+ "<|padding_token_10|>": 32012,
16
+ "<|padding_token_110|>": 32112,
17
+ "<|padding_token_111|>": 32113,
18
+ "<|padding_token_112|>": 32114,
19
+ "<|padding_token_113|>": 32115,
20
+ "<|padding_token_114|>": 32116,
21
+ "<|padding_token_115|>": 32117,
22
+ "<|padding_token_116|>": 32118,
23
+ "<|padding_token_117|>": 32119,
24
+ "<|padding_token_118|>": 32120,
25
+ "<|padding_token_119|>": 32121,
26
+ "<|padding_token_11|>": 32013,
27
+ "<|padding_token_120|>": 32122,
28
+ "<|padding_token_121|>": 32123,
29
+ "<|padding_token_122|>": 32124,
30
+ "<|padding_token_123|>": 32125,
31
+ "<|padding_token_124|>": 32126,
32
+ "<|padding_token_125|>": 32127,
33
+ "<|padding_token_12|>": 32014,
34
+ "<|padding_token_13|>": 32015,
35
+ "<|padding_token_14|>": 32016,
36
+ "<|padding_token_15|>": 32017,
37
+ "<|padding_token_16|>": 32018,
38
+ "<|padding_token_17|>": 32019,
39
+ "<|padding_token_18|>": 32020,
40
+ "<|padding_token_19|>": 32021,
41
+ "<|padding_token_1|>": 32003,
42
+ "<|padding_token_20|>": 32022,
43
+ "<|padding_token_21|>": 32023,
44
+ "<|padding_token_22|>": 32024,
45
+ "<|padding_token_23|>": 32025,
46
+ "<|padding_token_24|>": 32026,
47
+ "<|padding_token_25|>": 32027,
48
+ "<|padding_token_26|>": 32028,
49
+ "<|padding_token_27|>": 32029,
50
+ "<|padding_token_28|>": 32030,
51
+ "<|padding_token_29|>": 32031,
52
+ "<|padding_token_2|>": 32004,
53
+ "<|padding_token_30|>": 32032,
54
+ "<|padding_token_31|>": 32033,
55
+ "<|padding_token_32|>": 32034,
56
+ "<|padding_token_33|>": 32035,
57
+ "<|padding_token_34|>": 32036,
58
+ "<|padding_token_35|>": 32037,
59
+ "<|padding_token_36|>": 32038,
60
+ "<|padding_token_37|>": 32039,
61
+ "<|padding_token_38|>": 32040,
62
+ "<|padding_token_39|>": 32041,
63
+ "<|padding_token_3|>": 32005,
64
+ "<|padding_token_40|>": 32042,
65
+ "<|padding_token_41|>": 32043,
66
+ "<|padding_token_42|>": 32044,
67
+ "<|padding_token_43|>": 32045,
68
+ "<|padding_token_44|>": 32046,
69
+ "<|padding_token_45|>": 32047,
70
+ "<|padding_token_46|>": 32048,
71
+ "<|padding_token_47|>": 32049,
72
+ "<|padding_token_48|>": 32050,
73
+ "<|padding_token_49|>": 32051,
74
+ "<|padding_token_4|>": 32006,
75
+ "<|padding_token_50|>": 32052,
76
+ "<|padding_token_51|>": 32053,
77
+ "<|padding_token_52|>": 32054,
78
+ "<|padding_token_53|>": 32055,
79
+ "<|padding_token_54|>": 32056,
80
+ "<|padding_token_55|>": 32057,
81
+ "<|padding_token_56|>": 32058,
82
+ "<|padding_token_57|>": 32059,
83
+ "<|padding_token_58|>": 32060,
84
+ "<|padding_token_59|>": 32061,
85
+ "<|padding_token_5|>": 32007,
86
+ "<|padding_token_60|>": 32062,
87
+ "<|padding_token_61|>": 32063,
88
+ "<|padding_token_62|>": 32064,
89
+ "<|padding_token_63|>": 32065,
90
+ "<|padding_token_64|>": 32066,
91
+ "<|padding_token_65|>": 32067,
92
+ "<|padding_token_66|>": 32068,
93
+ "<|padding_token_67|>": 32069,
94
+ "<|padding_token_68|>": 32070,
95
+ "<|padding_token_69|>": 32071,
96
+ "<|padding_token_6|>": 32008,
97
+ "<|padding_token_70|>": 32072,
98
+ "<|padding_token_71|>": 32073,
99
+ "<|padding_token_72|>": 32074,
100
+ "<|padding_token_73|>": 32075,
101
+ "<|padding_token_74|>": 32076,
102
+ "<|padding_token_75|>": 32077,
103
+ "<|padding_token_76|>": 32078,
104
+ "<|padding_token_77|>": 32079,
105
+ "<|padding_token_78|>": 32080,
106
+ "<|padding_token_79|>": 32081,
107
+ "<|padding_token_7|>": 32009,
108
+ "<|padding_token_80|>": 32082,
109
+ "<|padding_token_81|>": 32083,
110
+ "<|padding_token_82|>": 32084,
111
+ "<|padding_token_83|>": 32085,
112
+ "<|padding_token_84|>": 32086,
113
+ "<|padding_token_85|>": 32087,
114
+ "<|padding_token_86|>": 32088,
115
+ "<|padding_token_87|>": 32089,
116
+ "<|padding_token_88|>": 32090,
117
+ "<|padding_token_89|>": 32091,
118
+ "<|padding_token_8|>": 32010,
119
+ "<|padding_token_90|>": 32092,
120
+ "<|padding_token_91|>": 32093,
121
+ "<|padding_token_92|>": 32094,
122
+ "<|padding_token_93|>": 32095,
123
+ "<|padding_token_94|>": 32096,
124
+ "<|padding_token_95|>": 32097,
125
+ "<|padding_token_96|>": 32098,
126
+ "<|padding_token_97|>": 32099,
127
+ "<|padding_token_98|>": 32100,
128
+ "<|padding_token_99|>": 32101,
129
+ "<|padding_token_9|>": 32011
130
  }
special_tokens_map.json CHANGED
@@ -1,12 +1,39 @@
1
  {
2
  "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>",
6
- "<|im_start|>",
7
- "<|im_end|>"
 
 
 
 
 
 
 
 
 
8
  ],
9
- "bos_token": "<s>",
10
- "eos_token": "</s>",
11
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
  ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<unk>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
  }
tokenizer_config.json CHANGED
@@ -28,25 +28,1030 @@
28
  },
29
  "32000": {
30
  "content": "<|im_start|>",
31
- "lstrip": true,
32
  "normalized": false,
33
- "rstrip": true,
34
  "single_word": false,
35
  "special": true
36
  },
37
  "32001": {
38
  "content": "<|im_end|>",
39
- "lstrip": true,
40
  "normalized": false,
41
- "rstrip": true,
42
  "single_word": false,
43
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44
  }
45
  },
46
  "additional_special_tokens": [
47
- "<unk>",
48
- "<s>",
49
- "</s>",
50
  "<|im_start|>",
51
  "<|im_end|>"
52
  ],
@@ -60,7 +1065,6 @@
60
  "sp_model_kwargs": {},
61
  "spaces_between_special_tokens": false,
62
  "tokenizer_class": "LlamaTokenizer",
63
- "tokenizer_file": "/pfss/mlde/workspaces/mlde_wsp_Laion/huggingface/hub/models--bjoernp--leo-big/snapshots/0f9d0d2f9a16099cda0b3c25c175679c9628cdb1/tokenizer.json",
64
  "unk_token": "<unk>",
65
  "use_default_system_prompt": true
66
  }
 
28
  },
29
  "32000": {
30
  "content": "<|im_start|>",
31
+ "lstrip": false,
32
  "normalized": false,
33
+ "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
  "32001": {
38
  "content": "<|im_end|>",
39
+ "lstrip": false,
40
  "normalized": false,
41
+ "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|padding_token_0|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "32003": {
54
+ "content": "<|padding_token_1|>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "32004": {
62
+ "content": "<|padding_token_2|>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "32005": {
70
+ "content": "<|padding_token_3|>",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "32006": {
78
+ "content": "<|padding_token_4|>",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "32007": {
86
+ "content": "<|padding_token_5|>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "32008": {
94
+ "content": "<|padding_token_6|>",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "32009": {
102
+ "content": "<|padding_token_7|>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "32010": {
110
+ "content": "<|padding_token_8|>",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "32011": {
118
+ "content": "<|padding_token_9|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "32012": {
126
+ "content": "<|padding_token_10|>",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "32013": {
134
+ "content": "<|padding_token_11|>",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "32014": {
142
+ "content": "<|padding_token_12|>",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "32015": {
150
+ "content": "<|padding_token_13|>",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "32016": {
158
+ "content": "<|padding_token_14|>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "32017": {
166
+ "content": "<|padding_token_15|>",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "32018": {
174
+ "content": "<|padding_token_16|>",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "32019": {
182
+ "content": "<|padding_token_17|>",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "32020": {
190
+ "content": "<|padding_token_18|>",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "32021": {
198
+ "content": "<|padding_token_19|>",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "32022": {
206
+ "content": "<|padding_token_20|>",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "32023": {
214
+ "content": "<|padding_token_21|>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "32024": {
222
+ "content": "<|padding_token_22|>",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "32025": {
230
+ "content": "<|padding_token_23|>",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "32026": {
238
+ "content": "<|padding_token_24|>",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "32027": {
246
+ "content": "<|padding_token_25|>",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "32028": {
254
+ "content": "<|padding_token_26|>",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32029": {
262
+ "content": "<|padding_token_27|>",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "32030": {
270
+ "content": "<|padding_token_28|>",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "32031": {
278
+ "content": "<|padding_token_29|>",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "32032": {
286
+ "content": "<|padding_token_30|>",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "32033": {
294
+ "content": "<|padding_token_31|>",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "32034": {
302
+ "content": "<|padding_token_32|>",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "32035": {
310
+ "content": "<|padding_token_33|>",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "32036": {
318
+ "content": "<|padding_token_34|>",
319
+ "lstrip": false,
320
+ "normalized": true,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "32037": {
326
+ "content": "<|padding_token_35|>",
327
+ "lstrip": false,
328
+ "normalized": true,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "32038": {
334
+ "content": "<|padding_token_36|>",
335
+ "lstrip": false,
336
+ "normalized": true,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "32039": {
342
+ "content": "<|padding_token_37|>",
343
+ "lstrip": false,
344
+ "normalized": true,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "32040": {
350
+ "content": "<|padding_token_38|>",
351
+ "lstrip": false,
352
+ "normalized": true,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "32041": {
358
+ "content": "<|padding_token_39|>",
359
+ "lstrip": false,
360
+ "normalized": true,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "32042": {
366
+ "content": "<|padding_token_40|>",
367
+ "lstrip": false,
368
+ "normalized": true,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "32043": {
374
+ "content": "<|padding_token_41|>",
375
+ "lstrip": false,
376
+ "normalized": true,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "32044": {
382
+ "content": "<|padding_token_42|>",
383
+ "lstrip": false,
384
+ "normalized": true,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "32045": {
390
+ "content": "<|padding_token_43|>",
391
+ "lstrip": false,
392
+ "normalized": true,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "32046": {
398
+ "content": "<|padding_token_44|>",
399
+ "lstrip": false,
400
+ "normalized": true,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "32047": {
406
+ "content": "<|padding_token_45|>",
407
+ "lstrip": false,
408
+ "normalized": true,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "32048": {
414
+ "content": "<|padding_token_46|>",
415
+ "lstrip": false,
416
+ "normalized": true,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "32049": {
422
+ "content": "<|padding_token_47|>",
423
+ "lstrip": false,
424
+ "normalized": true,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "32050": {
430
+ "content": "<|padding_token_48|>",
431
+ "lstrip": false,
432
+ "normalized": true,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "32051": {
438
+ "content": "<|padding_token_49|>",
439
+ "lstrip": false,
440
+ "normalized": true,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "32052": {
446
+ "content": "<|padding_token_50|>",
447
+ "lstrip": false,
448
+ "normalized": true,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "32053": {
454
+ "content": "<|padding_token_51|>",
455
+ "lstrip": false,
456
+ "normalized": true,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "32054": {
462
+ "content": "<|padding_token_52|>",
463
+ "lstrip": false,
464
+ "normalized": true,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "32055": {
470
+ "content": "<|padding_token_53|>",
471
+ "lstrip": false,
472
+ "normalized": true,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "32056": {
478
+ "content": "<|padding_token_54|>",
479
+ "lstrip": false,
480
+ "normalized": true,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "32057": {
486
+ "content": "<|padding_token_55|>",
487
+ "lstrip": false,
488
+ "normalized": true,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "32058": {
494
+ "content": "<|padding_token_56|>",
495
+ "lstrip": false,
496
+ "normalized": true,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "32059": {
502
+ "content": "<|padding_token_57|>",
503
+ "lstrip": false,
504
+ "normalized": true,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "32060": {
510
+ "content": "<|padding_token_58|>",
511
+ "lstrip": false,
512
+ "normalized": true,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "32061": {
518
+ "content": "<|padding_token_59|>",
519
+ "lstrip": false,
520
+ "normalized": true,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "32062": {
526
+ "content": "<|padding_token_60|>",
527
+ "lstrip": false,
528
+ "normalized": true,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "32063": {
534
+ "content": "<|padding_token_61|>",
535
+ "lstrip": false,
536
+ "normalized": true,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "32064": {
542
+ "content": "<|padding_token_62|>",
543
+ "lstrip": false,
544
+ "normalized": true,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "32065": {
550
+ "content": "<|padding_token_63|>",
551
+ "lstrip": false,
552
+ "normalized": true,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "32066": {
558
+ "content": "<|padding_token_64|>",
559
+ "lstrip": false,
560
+ "normalized": true,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "32067": {
566
+ "content": "<|padding_token_65|>",
567
+ "lstrip": false,
568
+ "normalized": true,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "32068": {
574
+ "content": "<|padding_token_66|>",
575
+ "lstrip": false,
576
+ "normalized": true,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "32069": {
582
+ "content": "<|padding_token_67|>",
583
+ "lstrip": false,
584
+ "normalized": true,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "32070": {
590
+ "content": "<|padding_token_68|>",
591
+ "lstrip": false,
592
+ "normalized": true,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "32071": {
598
+ "content": "<|padding_token_69|>",
599
+ "lstrip": false,
600
+ "normalized": true,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "32072": {
606
+ "content": "<|padding_token_70|>",
607
+ "lstrip": false,
608
+ "normalized": true,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "32073": {
614
+ "content": "<|padding_token_71|>",
615
+ "lstrip": false,
616
+ "normalized": true,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "32074": {
622
+ "content": "<|padding_token_72|>",
623
+ "lstrip": false,
624
+ "normalized": true,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "32075": {
630
+ "content": "<|padding_token_73|>",
631
+ "lstrip": false,
632
+ "normalized": true,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "32076": {
638
+ "content": "<|padding_token_74|>",
639
+ "lstrip": false,
640
+ "normalized": true,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "32077": {
646
+ "content": "<|padding_token_75|>",
647
+ "lstrip": false,
648
+ "normalized": true,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "32078": {
654
+ "content": "<|padding_token_76|>",
655
+ "lstrip": false,
656
+ "normalized": true,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "32079": {
662
+ "content": "<|padding_token_77|>",
663
+ "lstrip": false,
664
+ "normalized": true,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "32080": {
670
+ "content": "<|padding_token_78|>",
671
+ "lstrip": false,
672
+ "normalized": true,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "32081": {
678
+ "content": "<|padding_token_79|>",
679
+ "lstrip": false,
680
+ "normalized": true,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "32082": {
686
+ "content": "<|padding_token_80|>",
687
+ "lstrip": false,
688
+ "normalized": true,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "32083": {
694
+ "content": "<|padding_token_81|>",
695
+ "lstrip": false,
696
+ "normalized": true,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "32084": {
702
+ "content": "<|padding_token_82|>",
703
+ "lstrip": false,
704
+ "normalized": true,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "32085": {
710
+ "content": "<|padding_token_83|>",
711
+ "lstrip": false,
712
+ "normalized": true,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "32086": {
718
+ "content": "<|padding_token_84|>",
719
+ "lstrip": false,
720
+ "normalized": true,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "32087": {
726
+ "content": "<|padding_token_85|>",
727
+ "lstrip": false,
728
+ "normalized": true,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "32088": {
734
+ "content": "<|padding_token_86|>",
735
+ "lstrip": false,
736
+ "normalized": true,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "32089": {
742
+ "content": "<|padding_token_87|>",
743
+ "lstrip": false,
744
+ "normalized": true,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "32090": {
750
+ "content": "<|padding_token_88|>",
751
+ "lstrip": false,
752
+ "normalized": true,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "32091": {
758
+ "content": "<|padding_token_89|>",
759
+ "lstrip": false,
760
+ "normalized": true,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "32092": {
766
+ "content": "<|padding_token_90|>",
767
+ "lstrip": false,
768
+ "normalized": true,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "32093": {
774
+ "content": "<|padding_token_91|>",
775
+ "lstrip": false,
776
+ "normalized": true,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "32094": {
782
+ "content": "<|padding_token_92|>",
783
+ "lstrip": false,
784
+ "normalized": true,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "32095": {
790
+ "content": "<|padding_token_93|>",
791
+ "lstrip": false,
792
+ "normalized": true,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "32096": {
798
+ "content": "<|padding_token_94|>",
799
+ "lstrip": false,
800
+ "normalized": true,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "32097": {
806
+ "content": "<|padding_token_95|>",
807
+ "lstrip": false,
808
+ "normalized": true,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "32098": {
814
+ "content": "<|padding_token_96|>",
815
+ "lstrip": false,
816
+ "normalized": true,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "32099": {
822
+ "content": "<|padding_token_97|>",
823
+ "lstrip": false,
824
+ "normalized": true,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "32100": {
830
+ "content": "<|padding_token_98|>",
831
+ "lstrip": false,
832
+ "normalized": true,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "32101": {
838
+ "content": "<|padding_token_99|>",
839
+ "lstrip": false,
840
+ "normalized": true,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "32102": {
846
+ "content": "<|padding_token_100|>",
847
+ "lstrip": false,
848
+ "normalized": true,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "32103": {
854
+ "content": "<|padding_token_101|>",
855
+ "lstrip": false,
856
+ "normalized": true,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "32104": {
862
+ "content": "<|padding_token_102|>",
863
+ "lstrip": false,
864
+ "normalized": true,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "32105": {
870
+ "content": "<|padding_token_103|>",
871
+ "lstrip": false,
872
+ "normalized": true,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "32106": {
878
+ "content": "<|padding_token_104|>",
879
+ "lstrip": false,
880
+ "normalized": true,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "32107": {
886
+ "content": "<|padding_token_105|>",
887
+ "lstrip": false,
888
+ "normalized": true,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "32108": {
894
+ "content": "<|padding_token_106|>",
895
+ "lstrip": false,
896
+ "normalized": true,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "32109": {
902
+ "content": "<|padding_token_107|>",
903
+ "lstrip": false,
904
+ "normalized": true,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "32110": {
910
+ "content": "<|padding_token_108|>",
911
+ "lstrip": false,
912
+ "normalized": true,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "32111": {
918
+ "content": "<|padding_token_109|>",
919
+ "lstrip": false,
920
+ "normalized": true,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "32112": {
926
+ "content": "<|padding_token_110|>",
927
+ "lstrip": false,
928
+ "normalized": true,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "32113": {
934
+ "content": "<|padding_token_111|>",
935
+ "lstrip": false,
936
+ "normalized": true,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "32114": {
942
+ "content": "<|padding_token_112|>",
943
+ "lstrip": false,
944
+ "normalized": true,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "32115": {
950
+ "content": "<|padding_token_113|>",
951
+ "lstrip": false,
952
+ "normalized": true,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "32116": {
958
+ "content": "<|padding_token_114|>",
959
+ "lstrip": false,
960
+ "normalized": true,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "32117": {
966
+ "content": "<|padding_token_115|>",
967
+ "lstrip": false,
968
+ "normalized": true,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "32118": {
974
+ "content": "<|padding_token_116|>",
975
+ "lstrip": false,
976
+ "normalized": true,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "32119": {
982
+ "content": "<|padding_token_117|>",
983
+ "lstrip": false,
984
+ "normalized": true,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "32120": {
990
+ "content": "<|padding_token_118|>",
991
+ "lstrip": false,
992
+ "normalized": true,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "32121": {
998
+ "content": "<|padding_token_119|>",
999
+ "lstrip": false,
1000
+ "normalized": true,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "32122": {
1006
+ "content": "<|padding_token_120|>",
1007
+ "lstrip": false,
1008
+ "normalized": true,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "32123": {
1014
+ "content": "<|padding_token_121|>",
1015
+ "lstrip": false,
1016
+ "normalized": true,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "32124": {
1022
+ "content": "<|padding_token_122|>",
1023
+ "lstrip": false,
1024
+ "normalized": true,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "32125": {
1030
+ "content": "<|padding_token_123|>",
1031
+ "lstrip": false,
1032
+ "normalized": true,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "32126": {
1038
+ "content": "<|padding_token_124|>",
1039
+ "lstrip": false,
1040
+ "normalized": true,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "32127": {
1046
+ "content": "<|padding_token_125|>",
1047
+ "lstrip": false,
1048
+ "normalized": true,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
  }
1053
  },
1054
  "additional_special_tokens": [
 
 
 
1055
  "<|im_start|>",
1056
  "<|im_end|>"
1057
  ],
 
1065
  "sp_model_kwargs": {},
1066
  "spaces_between_special_tokens": false,
1067
  "tokenizer_class": "LlamaTokenizer",
 
1068
  "unk_token": "<unk>",
1069
  "use_default_system_prompt": true
1070
  }