siruenyian commited on
Commit
75871d7
·
verified ·
1 Parent(s): f1c52e0

feat: add initial tokenizer (Trained with Unsloth)

Browse files
Files changed (3) hide show
  1. chat_template.jinja +118 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +784 -0
chat_template.jinja ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
+ {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
+ {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
+ {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
+ {%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
6
+ {%- if available_tools is defined and available_tools %}
7
+ {%- set tools = available_tools %}
8
+ {%- endif %}
9
+ {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
10
+ documents_system_message=documents_system_message_prefix,
11
+ default_system_message=g4_default_system_message,
12
+ system_message=''
13
+ ) %}
14
+ {%- if tools %}
15
+ {%- for tool in tools %}
16
+ {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
17
+ {%- endfor %}
18
+ {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
19
+ {%- else %}
20
+ {%- set ns.tools_system_message = '' %}
21
+ {%- endif %}
22
+ {%- if documents %}
23
+ {%- for document in documents %}
24
+ {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
25
+ {%- endfor %}
26
+ {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
27
+ {%- else %}
28
+ {%- set ns.documents_system_message = '' %}
29
+ {%- endif %}
30
+ {%- if messages[0].role == 'system' %}
31
+ {%- if messages[0].content is string %}
32
+ {%- set ns.system_message = messages[0].content %}
33
+ {%- elif messages[0].content is iterable %}
34
+ {%- for entry in messages[0].content %}
35
+ {%- if entry.type== 'text' %}
36
+ {%- if ns.system_message != '' %}
37
+ {%- set ns.system_message = ns.system_message + '\n' %}
38
+ {%- endif %}
39
+ {%- set ns.system_message = ns.system_message + entry.text %}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {%- endif %}
43
+ {%- if tools and documents %}
44
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
45
+ {%- elif tools %}
46
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
47
+ {%- elif documents %}
48
+ {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
49
+ {%- endif %}
50
+ {%- else %}
51
+ {%- if tools and documents %}
52
+ {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
53
+ {%- elif tools %}
54
+ {%- set ns.system_message = ns.tools_system_message %}
55
+ {%- elif documents %}
56
+ {%- set ns.system_message = ns.documents_system_message %}
57
+ {%- endif %}
58
+ {%- endif %}
59
+ {%- if ns.system_message %}
60
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
61
+ {%- else %}
62
+ {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
63
+ {%- endif %}
64
+ {%- for message in messages %}
65
+ {%- set content = namespace(val='') %}
66
+ {%- if message.content is string %}
67
+ {%- set content.val = message.content %}
68
+ {%- else %}
69
+ {%- if message.content is iterable %}
70
+ {%- for entry in message.content %}
71
+ {%- if entry.type== 'text' %}
72
+ {%- if content.val != '' %}
73
+ {%- set content.val = content.val + '\n' %}
74
+ {%- endif %}
75
+ {%- set content.val = content.val + entry.text %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- endif %}
79
+ {%- endif %}
80
+ {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
81
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
82
+ {%- elif message.role == 'assistant' %}
83
+ {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
84
+ {%- if message.tool_calls %}
85
+ {%- for tool_call in message.tool_calls %}
86
+ {%- if (loop.first and content.val) or (not loop.first) %}
87
+ {{- '\n' }}
88
+ {%- endif %}
89
+ {%- if tool_call.function %}
90
+ {%- set tool_call = tool_call.function %}
91
+ {%- endif %}
92
+ {{- '<tool_call>\n{"name": "' }}
93
+ {{- tool_call.name }}
94
+ {{- '", "arguments": ' }}
95
+ {%- if tool_call.arguments is string %}
96
+ {{- tool_call.arguments }}
97
+ {%- else %}
98
+ {{- tool_call.arguments | tojson }}
99
+ {%- endif %}
100
+ {{- '}\n</tool_call>' }}
101
+ {%- endfor %}
102
+ {%- endif %}
103
+ {{- '<|end_of_text|>\n' }}
104
+ {%- elif message.role == 'tool' %}
105
+ {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
106
+ {{- '<|start_of_role|>user<|end_of_role|>' }}
107
+ {%- endif %}
108
+ {{- '\n<tool_response>\n' }}
109
+ {{- content.val }}
110
+ {{- '\n</tool_response>' }}
111
+ {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
112
+ {{- '<|end_of_text|>\n' }}
113
+ {%- endif %}
114
+ {%- endif %}
115
+ {%- endfor %}
116
+ {%- if add_generation_prompt %}
117
+ {{- '<|start_of_role|>assistant<|end_of_role|>' }}
118
+ {%- endif %}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,784 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|end_of_text|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|end_of_text|>",
7
+ "errors": "replace",
8
+ "is_local": true,
9
+ "model_max_length": 32768,
10
+ "pad_token": "<|pad|>",
11
+ "padding_side": "left",
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|unk|>",
14
+ "added_tokens_decoder": {
15
+ "100256": {
16
+ "content": "<|pad|>",
17
+ "single_word": false,
18
+ "lstrip": false,
19
+ "rstrip": false,
20
+ "normalized": false,
21
+ "special": true
22
+ },
23
+ "100257": {
24
+ "content": "<|end_of_text|>",
25
+ "single_word": false,
26
+ "lstrip": false,
27
+ "rstrip": false,
28
+ "normalized": false,
29
+ "special": true
30
+ },
31
+ "100258": {
32
+ "content": "<|fim_prefix|>",
33
+ "single_word": false,
34
+ "lstrip": false,
35
+ "rstrip": false,
36
+ "normalized": false,
37
+ "special": false
38
+ },
39
+ "100259": {
40
+ "content": "<|fim_middle|>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": false
46
+ },
47
+ "100260": {
48
+ "content": "<|fim_suffix|>",
49
+ "single_word": false,
50
+ "lstrip": false,
51
+ "rstrip": false,
52
+ "normalized": false,
53
+ "special": false
54
+ },
55
+ "100261": {
56
+ "content": "<|fim_pad|>",
57
+ "single_word": false,
58
+ "lstrip": false,
59
+ "rstrip": false,
60
+ "normalized": false,
61
+ "special": false
62
+ },
63
+ "100262": {
64
+ "content": "<|filename|>",
65
+ "single_word": false,
66
+ "lstrip": false,
67
+ "rstrip": false,
68
+ "normalized": false,
69
+ "special": false
70
+ },
71
+ "100263": {
72
+ "content": "<|reponame|>",
73
+ "single_word": false,
74
+ "lstrip": false,
75
+ "rstrip": false,
76
+ "normalized": false,
77
+ "special": false
78
+ },
79
+ "100264": {
80
+ "content": "<|start_of_role|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ "100265": {
88
+ "content": "<|end_of_role|>",
89
+ "single_word": false,
90
+ "lstrip": false,
91
+ "rstrip": false,
92
+ "normalized": false,
93
+ "special": true
94
+ },
95
+ "100266": {
96
+ "content": "<|unused_1|>",
97
+ "single_word": false,
98
+ "lstrip": false,
99
+ "rstrip": false,
100
+ "normalized": false,
101
+ "special": true
102
+ },
103
+ "100267": {
104
+ "content": "<|start_of_plugin|>",
105
+ "single_word": false,
106
+ "lstrip": false,
107
+ "rstrip": false,
108
+ "normalized": false,
109
+ "special": true
110
+ },
111
+ "100268": {
112
+ "content": "<|end_of_plugin|>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": false,
117
+ "special": true
118
+ },
119
+ "100269": {
120
+ "content": "<|unk|>",
121
+ "single_word": false,
122
+ "lstrip": false,
123
+ "rstrip": false,
124
+ "normalized": false,
125
+ "special": true
126
+ },
127
+ "100270": {
128
+ "content": "<tool_call>",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": false,
133
+ "special": false
134
+ },
135
+ "100271": {
136
+ "content": "</tool_call>",
137
+ "single_word": false,
138
+ "lstrip": false,
139
+ "rstrip": false,
140
+ "normalized": false,
141
+ "special": false
142
+ },
143
+ "100272": {
144
+ "content": "<tool_response>",
145
+ "single_word": false,
146
+ "lstrip": false,
147
+ "rstrip": false,
148
+ "normalized": false,
149
+ "special": false
150
+ },
151
+ "100273": {
152
+ "content": "</tool_response>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": false
158
+ },
159
+ "100274": {
160
+ "content": "<think>",
161
+ "single_word": false,
162
+ "lstrip": false,
163
+ "rstrip": false,
164
+ "normalized": false,
165
+ "special": false
166
+ },
167
+ "100275": {
168
+ "content": "</think>",
169
+ "single_word": false,
170
+ "lstrip": false,
171
+ "rstrip": false,
172
+ "normalized": false,
173
+ "special": false
174
+ },
175
+ "100276": {
176
+ "content": "<think_on>",
177
+ "single_word": false,
178
+ "lstrip": false,
179
+ "rstrip": false,
180
+ "normalized": false,
181
+ "special": true
182
+ },
183
+ "100277": {
184
+ "content": "<think_off>",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": false,
189
+ "special": true
190
+ },
191
+ "100278": {
192
+ "content": "<schema>",
193
+ "single_word": false,
194
+ "lstrip": false,
195
+ "rstrip": false,
196
+ "normalized": false,
197
+ "special": true
198
+ },
199
+ "100279": {
200
+ "content": "</schema>",
201
+ "single_word": false,
202
+ "lstrip": false,
203
+ "rstrip": false,
204
+ "normalized": false,
205
+ "special": true
206
+ },
207
+ "100280": {
208
+ "content": "<tools>",
209
+ "single_word": false,
210
+ "lstrip": false,
211
+ "rstrip": false,
212
+ "normalized": false,
213
+ "special": true
214
+ },
215
+ "100281": {
216
+ "content": "</tools>",
217
+ "single_word": false,
218
+ "lstrip": false,
219
+ "rstrip": false,
220
+ "normalized": false,
221
+ "special": true
222
+ },
223
+ "100282": {
224
+ "content": "<documents>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ "100283": {
232
+ "content": "</documents>",
233
+ "single_word": false,
234
+ "lstrip": false,
235
+ "rstrip": false,
236
+ "normalized": false,
237
+ "special": true
238
+ },
239
+ "100284": {
240
+ "content": "<|unused_15|>",
241
+ "single_word": false,
242
+ "lstrip": false,
243
+ "rstrip": false,
244
+ "normalized": false,
245
+ "special": true
246
+ },
247
+ "100285": {
248
+ "content": "<|unused_16|>",
249
+ "single_word": false,
250
+ "lstrip": false,
251
+ "rstrip": false,
252
+ "normalized": false,
253
+ "special": true
254
+ },
255
+ "100286": {
256
+ "content": "<|unused_17|>",
257
+ "single_word": false,
258
+ "lstrip": false,
259
+ "rstrip": false,
260
+ "normalized": false,
261
+ "special": true
262
+ },
263
+ "100287": {
264
+ "content": "<|unused_18|>",
265
+ "single_word": false,
266
+ "lstrip": false,
267
+ "rstrip": false,
268
+ "normalized": false,
269
+ "special": true
270
+ },
271
+ "100288": {
272
+ "content": "<|unused_19|>",
273
+ "single_word": false,
274
+ "lstrip": false,
275
+ "rstrip": false,
276
+ "normalized": false,
277
+ "special": true
278
+ },
279
+ "100289": {
280
+ "content": "<|unused_20|>",
281
+ "single_word": false,
282
+ "lstrip": false,
283
+ "rstrip": false,
284
+ "normalized": false,
285
+ "special": true
286
+ },
287
+ "100290": {
288
+ "content": "<|unused_21|>",
289
+ "single_word": false,
290
+ "lstrip": false,
291
+ "rstrip": false,
292
+ "normalized": false,
293
+ "special": true
294
+ },
295
+ "100291": {
296
+ "content": "<|unused_22|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ "100292": {
304
+ "content": "<|unused_23|>",
305
+ "single_word": false,
306
+ "lstrip": false,
307
+ "rstrip": false,
308
+ "normalized": false,
309
+ "special": true
310
+ },
311
+ "100293": {
312
+ "content": "<|unused_24|>",
313
+ "single_word": false,
314
+ "lstrip": false,
315
+ "rstrip": false,
316
+ "normalized": false,
317
+ "special": true
318
+ },
319
+ "100294": {
320
+ "content": "<|unused_25|>",
321
+ "single_word": false,
322
+ "lstrip": false,
323
+ "rstrip": false,
324
+ "normalized": false,
325
+ "special": true
326
+ },
327
+ "100295": {
328
+ "content": "<|unused_26|>",
329
+ "single_word": false,
330
+ "lstrip": false,
331
+ "rstrip": false,
332
+ "normalized": false,
333
+ "special": true
334
+ },
335
+ "100296": {
336
+ "content": "<|unused_27|>",
337
+ "single_word": false,
338
+ "lstrip": false,
339
+ "rstrip": false,
340
+ "normalized": false,
341
+ "special": true
342
+ },
343
+ "100297": {
344
+ "content": "<|unused_28|>",
345
+ "single_word": false,
346
+ "lstrip": false,
347
+ "rstrip": false,
348
+ "normalized": false,
349
+ "special": true
350
+ },
351
+ "100298": {
352
+ "content": "<|unused_29|>",
353
+ "single_word": false,
354
+ "lstrip": false,
355
+ "rstrip": false,
356
+ "normalized": false,
357
+ "special": true
358
+ },
359
+ "100299": {
360
+ "content": "<|unused_30|>",
361
+ "single_word": false,
362
+ "lstrip": false,
363
+ "rstrip": false,
364
+ "normalized": false,
365
+ "special": true
366
+ },
367
+ "100300": {
368
+ "content": "<|unused_31|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ "100301": {
376
+ "content": "<|unused_32|>",
377
+ "single_word": false,
378
+ "lstrip": false,
379
+ "rstrip": false,
380
+ "normalized": false,
381
+ "special": true
382
+ },
383
+ "100302": {
384
+ "content": "<|unused_33|>",
385
+ "single_word": false,
386
+ "lstrip": false,
387
+ "rstrip": false,
388
+ "normalized": false,
389
+ "special": true
390
+ },
391
+ "100303": {
392
+ "content": "<|unused_34|>",
393
+ "single_word": false,
394
+ "lstrip": false,
395
+ "rstrip": false,
396
+ "normalized": false,
397
+ "special": true
398
+ },
399
+ "100304": {
400
+ "content": "<|unused_35|>",
401
+ "single_word": false,
402
+ "lstrip": false,
403
+ "rstrip": false,
404
+ "normalized": false,
405
+ "special": true
406
+ },
407
+ "100305": {
408
+ "content": "<|unused_36|>",
409
+ "single_word": false,
410
+ "lstrip": false,
411
+ "rstrip": false,
412
+ "normalized": false,
413
+ "special": true
414
+ },
415
+ "100306": {
416
+ "content": "<|unused_37|>",
417
+ "single_word": false,
418
+ "lstrip": false,
419
+ "rstrip": false,
420
+ "normalized": false,
421
+ "special": true
422
+ },
423
+ "100307": {
424
+ "content": "<|unused_38|>",
425
+ "single_word": false,
426
+ "lstrip": false,
427
+ "rstrip": false,
428
+ "normalized": false,
429
+ "special": true
430
+ },
431
+ "100308": {
432
+ "content": "<|unused_39|>",
433
+ "single_word": false,
434
+ "lstrip": false,
435
+ "rstrip": false,
436
+ "normalized": false,
437
+ "special": true
438
+ },
439
+ "100309": {
440
+ "content": "<|unused_40|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ "100310": {
448
+ "content": "<|unused_41|>",
449
+ "single_word": false,
450
+ "lstrip": false,
451
+ "rstrip": false,
452
+ "normalized": false,
453
+ "special": true
454
+ },
455
+ "100311": {
456
+ "content": "<|unused_42|>",
457
+ "single_word": false,
458
+ "lstrip": false,
459
+ "rstrip": false,
460
+ "normalized": false,
461
+ "special": true
462
+ },
463
+ "100312": {
464
+ "content": "<|unused_43|>",
465
+ "single_word": false,
466
+ "lstrip": false,
467
+ "rstrip": false,
468
+ "normalized": false,
469
+ "special": true
470
+ },
471
+ "100313": {
472
+ "content": "<|unused_44|>",
473
+ "single_word": false,
474
+ "lstrip": false,
475
+ "rstrip": false,
476
+ "normalized": false,
477
+ "special": true
478
+ },
479
+ "100314": {
480
+ "content": "<|unused_45|>",
481
+ "single_word": false,
482
+ "lstrip": false,
483
+ "rstrip": false,
484
+ "normalized": false,
485
+ "special": true
486
+ },
487
+ "100315": {
488
+ "content": "<|unused_46|>",
489
+ "single_word": false,
490
+ "lstrip": false,
491
+ "rstrip": false,
492
+ "normalized": false,
493
+ "special": true
494
+ },
495
+ "100316": {
496
+ "content": "<|unused_47|>",
497
+ "single_word": false,
498
+ "lstrip": false,
499
+ "rstrip": false,
500
+ "normalized": false,
501
+ "special": true
502
+ },
503
+ "100317": {
504
+ "content": "<|unused_48|>",
505
+ "single_word": false,
506
+ "lstrip": false,
507
+ "rstrip": false,
508
+ "normalized": false,
509
+ "special": true
510
+ },
511
+ "100318": {
512
+ "content": "<|unused_49|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ "100319": {
520
+ "content": "<|unused_50|>",
521
+ "single_word": false,
522
+ "lstrip": false,
523
+ "rstrip": false,
524
+ "normalized": false,
525
+ "special": true
526
+ },
527
+ "100320": {
528
+ "content": "<|unused_51|>",
529
+ "single_word": false,
530
+ "lstrip": false,
531
+ "rstrip": false,
532
+ "normalized": false,
533
+ "special": true
534
+ },
535
+ "100321": {
536
+ "content": "<|unused_52|>",
537
+ "single_word": false,
538
+ "lstrip": false,
539
+ "rstrip": false,
540
+ "normalized": false,
541
+ "special": true
542
+ },
543
+ "100322": {
544
+ "content": "<|unused_53|>",
545
+ "single_word": false,
546
+ "lstrip": false,
547
+ "rstrip": false,
548
+ "normalized": false,
549
+ "special": true
550
+ },
551
+ "100323": {
552
+ "content": "<|unused_54|>",
553
+ "single_word": false,
554
+ "lstrip": false,
555
+ "rstrip": false,
556
+ "normalized": false,
557
+ "special": true
558
+ },
559
+ "100324": {
560
+ "content": "<|unused_55|>",
561
+ "single_word": false,
562
+ "lstrip": false,
563
+ "rstrip": false,
564
+ "normalized": false,
565
+ "special": true
566
+ },
567
+ "100325": {
568
+ "content": "<|unused_56|>",
569
+ "single_word": false,
570
+ "lstrip": false,
571
+ "rstrip": false,
572
+ "normalized": false,
573
+ "special": true
574
+ },
575
+ "100326": {
576
+ "content": "<|unused_57|>",
577
+ "single_word": false,
578
+ "lstrip": false,
579
+ "rstrip": false,
580
+ "normalized": false,
581
+ "special": true
582
+ },
583
+ "100327": {
584
+ "content": "<|unused_58|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ "100328": {
592
+ "content": "<|unused_59|>",
593
+ "single_word": false,
594
+ "lstrip": false,
595
+ "rstrip": false,
596
+ "normalized": false,
597
+ "special": true
598
+ },
599
+ "100329": {
600
+ "content": "<|unused_60|>",
601
+ "single_word": false,
602
+ "lstrip": false,
603
+ "rstrip": false,
604
+ "normalized": false,
605
+ "special": true
606
+ },
607
+ "100330": {
608
+ "content": "<|unused_61|>",
609
+ "single_word": false,
610
+ "lstrip": false,
611
+ "rstrip": false,
612
+ "normalized": false,
613
+ "special": true
614
+ },
615
+ "100331": {
616
+ "content": "<|unused_62|>",
617
+ "single_word": false,
618
+ "lstrip": false,
619
+ "rstrip": false,
620
+ "normalized": false,
621
+ "special": true
622
+ },
623
+ "100332": {
624
+ "content": "<|unused_63|>",
625
+ "single_word": false,
626
+ "lstrip": false,
627
+ "rstrip": false,
628
+ "normalized": false,
629
+ "special": true
630
+ },
631
+ "100333": {
632
+ "content": "<|unused_64|>",
633
+ "single_word": false,
634
+ "lstrip": false,
635
+ "rstrip": false,
636
+ "normalized": false,
637
+ "special": true
638
+ },
639
+ "100334": {
640
+ "content": "<|unused_65|>",
641
+ "single_word": false,
642
+ "lstrip": false,
643
+ "rstrip": false,
644
+ "normalized": false,
645
+ "special": true
646
+ },
647
+ "100335": {
648
+ "content": "<|unused_66|>",
649
+ "single_word": false,
650
+ "lstrip": false,
651
+ "rstrip": false,
652
+ "normalized": false,
653
+ "special": true
654
+ },
655
+ "100336": {
656
+ "content": "<|unused_67|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ "100337": {
664
+ "content": "<|unused_68|>",
665
+ "single_word": false,
666
+ "lstrip": false,
667
+ "rstrip": false,
668
+ "normalized": false,
669
+ "special": true
670
+ },
671
+ "100338": {
672
+ "content": "<|unused_69|>",
673
+ "single_word": false,
674
+ "lstrip": false,
675
+ "rstrip": false,
676
+ "normalized": false,
677
+ "special": true
678
+ },
679
+ "100339": {
680
+ "content": "<|unused_70|>",
681
+ "single_word": false,
682
+ "lstrip": false,
683
+ "rstrip": false,
684
+ "normalized": false,
685
+ "special": true
686
+ },
687
+ "100340": {
688
+ "content": "<|unused_71|>",
689
+ "single_word": false,
690
+ "lstrip": false,
691
+ "rstrip": false,
692
+ "normalized": false,
693
+ "special": true
694
+ },
695
+ "100341": {
696
+ "content": "<|unused_72|>",
697
+ "single_word": false,
698
+ "lstrip": false,
699
+ "rstrip": false,
700
+ "normalized": false,
701
+ "special": true
702
+ },
703
+ "100342": {
704
+ "content": "<|unused_73|>",
705
+ "single_word": false,
706
+ "lstrip": false,
707
+ "rstrip": false,
708
+ "normalized": false,
709
+ "special": true
710
+ },
711
+ "100343": {
712
+ "content": "<|unused_74|>",
713
+ "single_word": false,
714
+ "lstrip": false,
715
+ "rstrip": false,
716
+ "normalized": false,
717
+ "special": true
718
+ },
719
+ "100344": {
720
+ "content": "<|unused_75|>",
721
+ "single_word": false,
722
+ "lstrip": false,
723
+ "rstrip": false,
724
+ "normalized": false,
725
+ "special": true
726
+ },
727
+ "100345": {
728
+ "content": "<|unused_76|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ "100346": {
736
+ "content": "<|unused_77|>",
737
+ "single_word": false,
738
+ "lstrip": false,
739
+ "rstrip": false,
740
+ "normalized": false,
741
+ "special": true
742
+ },
743
+ "100347": {
744
+ "content": "<|unused_78|>",
745
+ "single_word": false,
746
+ "lstrip": false,
747
+ "rstrip": false,
748
+ "normalized": false,
749
+ "special": true
750
+ },
751
+ "100348": {
752
+ "content": "<|unused_79|>",
753
+ "single_word": false,
754
+ "lstrip": false,
755
+ "rstrip": false,
756
+ "normalized": false,
757
+ "special": true
758
+ },
759
+ "100349": {
760
+ "content": "<|unused_80|>",
761
+ "single_word": false,
762
+ "lstrip": false,
763
+ "rstrip": false,
764
+ "normalized": false,
765
+ "special": true
766
+ },
767
+ "100350": {
768
+ "content": "<|unused_81|>",
769
+ "single_word": false,
770
+ "lstrip": false,
771
+ "rstrip": false,
772
+ "normalized": false,
773
+ "special": true
774
+ },
775
+ "100351": {
776
+ "content": "<|unused_82|>",
777
+ "single_word": false,
778
+ "lstrip": false,
779
+ "rstrip": false,
780
+ "normalized": false,
781
+ "special": true
782
+ }
783
+ }
784
+ }