Mia Xia commited on
Commit
544e035
1 Parent(s): 05bce18

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +2068 -9
tokenizer.json CHANGED
@@ -29,6 +29,2067 @@
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
@@ -60,6 +2121,12 @@
60
  },
61
  {
62
  "type": "Fuse"
 
 
 
 
 
 
63
  }
64
  ]
65
  },
@@ -75,17 +2142,9 @@
75
  "<unk>": 0,
76
  "<|startoftext|>": 1,
77
  "<|endoftext|>": 2,
78
- "<|Human|>": 3,
79
- "<|Assistant|>": 4,
80
- "<|System|>": 5,
81
  "<|im_start|>": 6,
82
  "<|im_end|>": 7,
83
  "<|im_sep|>": 8,
84
- "<|reserved003|>": 9,
85
- "<|reserved004|>": 10,
86
- "<|reserved005|>": 11,
87
- "<|reserved006|>": 12,
88
- "<|reserved007|>": 13,
89
  "<fim_prefix>": 14,
90
  "<fim_middle>": 15,
91
  "<fim_suffix>": 16,
@@ -174105,4 +176164,4 @@
174105
  "现 今"
174106
  ]
174107
  }
174108
- }
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 6,
35
+ "content": "<|im_start|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 7,
44
+ "content": "<|im_end|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 8,
53
+ "content": "<|im_sep|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 14,
62
+ "content": "<fim_prefix>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 15,
71
+ "content": "<fim_middle>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 16,
80
+ "content": "<fim_suffix>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 16,
89
+ "content": "<fim_suffix>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 17,
98
+ "content": "<fim_pad>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 18,
107
+ "content": "<filename>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 19,
116
+ "content": "<gh_stars>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 20,
125
+ "content": "<issue_start>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 21,
134
+ "content": "<issue_comment>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 22,
143
+ "content": "<issue_closed>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 23,
152
+ "content": "<jupyter_start>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 24,
161
+ "content": "<jupyter_text>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 25,
170
+ "content": "<jupyter_code>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 26,
179
+ "content": "<jupyter_output>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 27,
188
+ "content": "<empty_output>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 28,
197
+ "content": "<commit_before>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 29,
206
+ "content": "<commit_msg>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 30,
215
+ "content": "<commit_after>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 31,
224
+ "content": "<reponame>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 32,
233
+ "content": "<h1>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 33,
242
+ "content": "<h1/>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 34,
251
+ "content": "</h1>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 35,
260
+ "content": "<h2>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 36,
269
+ "content": "<h2/>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 37,
278
+ "content": "</h2>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 38,
287
+ "content": "<h3>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 39,
296
+ "content": "<h3/>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 40,
305
+ "content": "</h3>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 41,
314
+ "content": "<h4>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 42,
323
+ "content": "<h4/>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 43,
332
+ "content": "</h4>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 44,
341
+ "content": "<h5>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 45,
350
+ "content": "<h5/>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 46,
359
+ "content": "</h5>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 47,
368
+ "content": "<br>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 48,
377
+ "content": "<br/>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 49,
386
+ "content": "</br>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 50,
395
+ "content": "<strong>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 51,
404
+ "content": "<strong/>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 52,
413
+ "content": "</strong>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 53,
422
+ "content": "<p>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 54,
431
+ "content": "<p/>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 55,
440
+ "content": "</p>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 56,
449
+ "content": "<table>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 57,
458
+ "content": "<table/>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 58,
467
+ "content": "</table>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 59,
476
+ "content": "<li>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 60,
485
+ "content": "<li/>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 61,
494
+ "content": "</li>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 62,
503
+ "content": "<tr>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 63,
512
+ "content": "<tr/>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 64,
521
+ "content": "</tr>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 65,
530
+ "content": "<tbody>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 66,
539
+ "content": "<tbody/>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 67,
548
+ "content": "</tbody>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 68,
557
+ "content": "<img>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 69,
566
+ "content": "<img/>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 70,
575
+ "content": "</img>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 71,
584
+ "content": "<b>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 72,
593
+ "content": "<b/>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 73,
602
+ "content": "</b>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 74,
611
+ "content": "<td>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 75,
620
+ "content": "<td/>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 76,
629
+ "content": "</td>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 115,
638
+ "content": "<!--",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 118,
647
+ "content": "<!DOCTYPE>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 145,
656
+ "content": "<|unused000|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 146,
665
+ "content": "<|unused001|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 147,
674
+ "content": "<|unused002|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 148,
683
+ "content": "<|unused003|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 149,
692
+ "content": "<|unused004|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 150,
701
+ "content": "<|unused005|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 151,
710
+ "content": "<|unused006|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 152,
719
+ "content": "<|unused007|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 153,
728
+ "content": "<|unused008|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 154,
737
+ "content": "<|unused009|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 155,
746
+ "content": "<|unused010|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 156,
755
+ "content": "<|unused011|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 157,
764
+ "content": "<|unused012|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 158,
773
+ "content": "<|unused013|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 159,
782
+ "content": "<|unused014|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 160,
791
+ "content": "<|unused015|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 161,
800
+ "content": "<|unused016|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 162,
809
+ "content": "<|unused017|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 163,
818
+ "content": "<|unused018|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 164,
827
+ "content": "<|unused019|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 165,
836
+ "content": "<|unused020|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 166,
845
+ "content": "<|unused021|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 167,
854
+ "content": "<|unused022|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 168,
863
+ "content": "<|unused023|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 169,
872
+ "content": "<|unused024|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 170,
881
+ "content": "<|unused025|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 171,
890
+ "content": "<|unused026|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 172,
899
+ "content": "<|unused027|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 173,
908
+ "content": "<|unused028|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 174,
917
+ "content": "<|unused029|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 175,
926
+ "content": "<|unused030|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 176,
935
+ "content": "<|unused031|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ },
942
+ {
943
+ "id": 177,
944
+ "content": "<|unused032|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": false,
949
+ "special": true
950
+ },
951
+ {
952
+ "id": 178,
953
+ "content": "<|unused033|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": false,
958
+ "special": true
959
+ },
960
+ {
961
+ "id": 179,
962
+ "content": "<|unused034|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": false,
967
+ "special": true
968
+ },
969
+ {
970
+ "id": 180,
971
+ "content": "<|unused035|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": false,
976
+ "special": true
977
+ },
978
+ {
979
+ "id": 181,
980
+ "content": "<|unused036|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": false,
985
+ "special": true
986
+ },
987
+ {
988
+ "id": 182,
989
+ "content": "<|unused037|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": false,
994
+ "special": true
995
+ },
996
+ {
997
+ "id": 183,
998
+ "content": "<|unused038|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": false,
1003
+ "special": true
1004
+ },
1005
+ {
1006
+ "id": 184,
1007
+ "content": "<|unused039|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": false,
1012
+ "special": true
1013
+ },
1014
+ {
1015
+ "id": 185,
1016
+ "content": "<|unused040|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": false,
1021
+ "special": true
1022
+ },
1023
+ {
1024
+ "id": 186,
1025
+ "content": "<|unused041|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": false,
1030
+ "special": true
1031
+ },
1032
+ {
1033
+ "id": 187,
1034
+ "content": "<|unused042|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": false,
1039
+ "special": true
1040
+ },
1041
+ {
1042
+ "id": 188,
1043
+ "content": "<|unused043|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": false,
1048
+ "special": true
1049
+ },
1050
+ {
1051
+ "id": 189,
1052
+ "content": "<|unused044|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": false,
1057
+ "special": true
1058
+ },
1059
+ {
1060
+ "id": 190,
1061
+ "content": "<|unused045|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": false,
1066
+ "special": true
1067
+ },
1068
+ {
1069
+ "id": 191,
1070
+ "content": "<|unused046|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": false,
1075
+ "special": true
1076
+ },
1077
+ {
1078
+ "id": 192,
1079
+ "content": "<|unused047|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": false,
1084
+ "special": true
1085
+ },
1086
+ {
1087
+ "id": 193,
1088
+ "content": "<|unused048|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": false,
1093
+ "special": true
1094
+ },
1095
+ {
1096
+ "id": 194,
1097
+ "content": "<|unused049|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": false,
1102
+ "special": true
1103
+ },
1104
+ {
1105
+ "id": 195,
1106
+ "content": "<|unused050|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": false,
1111
+ "special": true
1112
+ },
1113
+ {
1114
+ "id": 196,
1115
+ "content": "<|unused051|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": false,
1120
+ "special": true
1121
+ },
1122
+ {
1123
+ "id": 197,
1124
+ "content": "<|unused052|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": false,
1129
+ "special": true
1130
+ },
1131
+ {
1132
+ "id": 198,
1133
+ "content": "<|unused053|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": false,
1138
+ "special": true
1139
+ },
1140
+ {
1141
+ "id": 199,
1142
+ "content": "<|unused054|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": false,
1147
+ "special": true
1148
+ },
1149
+ {
1150
+ "id": 200,
1151
+ "content": "<|unused055|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": false,
1156
+ "special": true
1157
+ },
1158
+ {
1159
+ "id": 201,
1160
+ "content": "<|unused056|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": false,
1165
+ "special": true
1166
+ },
1167
+ {
1168
+ "id": 202,
1169
+ "content": "<|unused057|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": false,
1174
+ "special": true
1175
+ },
1176
+ {
1177
+ "id": 203,
1178
+ "content": "<|unused058|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": false,
1183
+ "special": true
1184
+ },
1185
+ {
1186
+ "id": 204,
1187
+ "content": "<|unused059|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": false,
1192
+ "special": true
1193
+ },
1194
+ {
1195
+ "id": 205,
1196
+ "content": "<|unused060|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": false,
1201
+ "special": true
1202
+ },
1203
+ {
1204
+ "id": 206,
1205
+ "content": "<|unused061|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": false,
1210
+ "special": true
1211
+ },
1212
+ {
1213
+ "id": 207,
1214
+ "content": "<|unused062|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": false,
1219
+ "special": true
1220
+ },
1221
+ {
1222
+ "id": 208,
1223
+ "content": "<|unused063|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": false,
1228
+ "special": true
1229
+ },
1230
+ {
1231
+ "id": 209,
1232
+ "content": "<|unused064|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": false,
1237
+ "special": true
1238
+ },
1239
+ {
1240
+ "id": 210,
1241
+ "content": "<|unused065|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": false,
1246
+ "special": true
1247
+ },
1248
+ {
1249
+ "id": 211,
1250
+ "content": "<|unused066|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": false,
1255
+ "special": true
1256
+ },
1257
+ {
1258
+ "id": 212,
1259
+ "content": "<|unused067|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": false,
1264
+ "special": true
1265
+ },
1266
+ {
1267
+ "id": 213,
1268
+ "content": "<|unused068|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": false,
1273
+ "special": true
1274
+ },
1275
+ {
1276
+ "id": 214,
1277
+ "content": "<|unused069|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": false,
1282
+ "special": true
1283
+ },
1284
+ {
1285
+ "id": 215,
1286
+ "content": "<|unused070|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": false,
1291
+ "special": true
1292
+ },
1293
+ {
1294
+ "id": 216,
1295
+ "content": "<|unused071|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": false,
1300
+ "special": true
1301
+ },
1302
+ {
1303
+ "id": 217,
1304
+ "content": "<|unused072|>",
1305
+ "single_word": false,
1306
+ "lstrip": false,
1307
+ "rstrip": false,
1308
+ "normalized": false,
1309
+ "special": true
1310
+ },
1311
+ {
1312
+ "id": 218,
1313
+ "content": "<|unused073|>",
1314
+ "single_word": false,
1315
+ "lstrip": false,
1316
+ "rstrip": false,
1317
+ "normalized": false,
1318
+ "special": true
1319
+ },
1320
+ {
1321
+ "id": 219,
1322
+ "content": "<|unused074|>",
1323
+ "single_word": false,
1324
+ "lstrip": false,
1325
+ "rstrip": false,
1326
+ "normalized": false,
1327
+ "special": true
1328
+ },
1329
+ {
1330
+ "id": 220,
1331
+ "content": "<|unused075|>",
1332
+ "single_word": false,
1333
+ "lstrip": false,
1334
+ "rstrip": false,
1335
+ "normalized": false,
1336
+ "special": true
1337
+ },
1338
+ {
1339
+ "id": 221,
1340
+ "content": "<|unused076|>",
1341
+ "single_word": false,
1342
+ "lstrip": false,
1343
+ "rstrip": false,
1344
+ "normalized": false,
1345
+ "special": true
1346
+ },
1347
+ {
1348
+ "id": 222,
1349
+ "content": "<|unused077|>",
1350
+ "single_word": false,
1351
+ "lstrip": false,
1352
+ "rstrip": false,
1353
+ "normalized": false,
1354
+ "special": true
1355
+ },
1356
+ {
1357
+ "id": 223,
1358
+ "content": "<|unused078|>",
1359
+ "single_word": false,
1360
+ "lstrip": false,
1361
+ "rstrip": false,
1362
+ "normalized": false,
1363
+ "special": true
1364
+ },
1365
+ {
1366
+ "id": 224,
1367
+ "content": "<|unused079|>",
1368
+ "single_word": false,
1369
+ "lstrip": false,
1370
+ "rstrip": false,
1371
+ "normalized": false,
1372
+ "special": true
1373
+ },
1374
+ {
1375
+ "id": 225,
1376
+ "content": "<|unused080|>",
1377
+ "single_word": false,
1378
+ "lstrip": false,
1379
+ "rstrip": false,
1380
+ "normalized": false,
1381
+ "special": true
1382
+ },
1383
+ {
1384
+ "id": 226,
1385
+ "content": "<|unused081|>",
1386
+ "single_word": false,
1387
+ "lstrip": false,
1388
+ "rstrip": false,
1389
+ "normalized": false,
1390
+ "special": true
1391
+ },
1392
+ {
1393
+ "id": 227,
1394
+ "content": "<|unused082|>",
1395
+ "single_word": false,
1396
+ "lstrip": false,
1397
+ "rstrip": false,
1398
+ "normalized": false,
1399
+ "special": true
1400
+ },
1401
+ {
1402
+ "id": 228,
1403
+ "content": "<|unused083|>",
1404
+ "single_word": false,
1405
+ "lstrip": false,
1406
+ "rstrip": false,
1407
+ "normalized": false,
1408
+ "special": true
1409
+ },
1410
+ {
1411
+ "id": 229,
1412
+ "content": "<|unused084|>",
1413
+ "single_word": false,
1414
+ "lstrip": false,
1415
+ "rstrip": false,
1416
+ "normalized": false,
1417
+ "special": true
1418
+ },
1419
+ {
1420
+ "id": 230,
1421
+ "content": "<|unused085|>",
1422
+ "single_word": false,
1423
+ "lstrip": false,
1424
+ "rstrip": false,
1425
+ "normalized": false,
1426
+ "special": true
1427
+ },
1428
+ {
1429
+ "id": 231,
1430
+ "content": "<|unused086|>",
1431
+ "single_word": false,
1432
+ "lstrip": false,
1433
+ "rstrip": false,
1434
+ "normalized": false,
1435
+ "special": true
1436
+ },
1437
+ {
1438
+ "id": 232,
1439
+ "content": "<|unused087|>",
1440
+ "single_word": false,
1441
+ "lstrip": false,
1442
+ "rstrip": false,
1443
+ "normalized": false,
1444
+ "special": true
1445
+ },
1446
+ {
1447
+ "id": 233,
1448
+ "content": "<|unused088|>",
1449
+ "single_word": false,
1450
+ "lstrip": false,
1451
+ "rstrip": false,
1452
+ "normalized": false,
1453
+ "special": true
1454
+ },
1455
+ {
1456
+ "id": 234,
1457
+ "content": "<|unused089|>",
1458
+ "single_word": false,
1459
+ "lstrip": false,
1460
+ "rstrip": false,
1461
+ "normalized": false,
1462
+ "special": true
1463
+ },
1464
+ {
1465
+ "id": 235,
1466
+ "content": "<|unused090|>",
1467
+ "single_word": false,
1468
+ "lstrip": false,
1469
+ "rstrip": false,
1470
+ "normalized": false,
1471
+ "special": true
1472
+ },
1473
+ {
1474
+ "id": 236,
1475
+ "content": "<|unused091|>",
1476
+ "single_word": false,
1477
+ "lstrip": false,
1478
+ "rstrip": false,
1479
+ "normalized": false,
1480
+ "special": true
1481
+ },
1482
+ {
1483
+ "id": 237,
1484
+ "content": "<|unused092|>",
1485
+ "single_word": false,
1486
+ "lstrip": false,
1487
+ "rstrip": false,
1488
+ "normalized": false,
1489
+ "special": true
1490
+ },
1491
+ {
1492
+ "id": 238,
1493
+ "content": "<|unused093|>",
1494
+ "single_word": false,
1495
+ "lstrip": false,
1496
+ "rstrip": false,
1497
+ "normalized": false,
1498
+ "special": true
1499
+ },
1500
+ {
1501
+ "id": 239,
1502
+ "content": "<|unused094|>",
1503
+ "single_word": false,
1504
+ "lstrip": false,
1505
+ "rstrip": false,
1506
+ "normalized": false,
1507
+ "special": true
1508
+ },
1509
+ {
1510
+ "id": 240,
1511
+ "content": "<|unused095|>",
1512
+ "single_word": false,
1513
+ "lstrip": false,
1514
+ "rstrip": false,
1515
+ "normalized": false,
1516
+ "special": true
1517
+ },
1518
+ {
1519
+ "id": 241,
1520
+ "content": "<|unused096|>",
1521
+ "single_word": false,
1522
+ "lstrip": false,
1523
+ "rstrip": false,
1524
+ "normalized": false,
1525
+ "special": true
1526
+ },
1527
+ {
1528
+ "id": 242,
1529
+ "content": "<|unused097|>",
1530
+ "single_word": false,
1531
+ "lstrip": false,
1532
+ "rstrip": false,
1533
+ "normalized": false,
1534
+ "special": true
1535
+ },
1536
+ {
1537
+ "id": 243,
1538
+ "content": "<|unused098|>",
1539
+ "single_word": false,
1540
+ "lstrip": false,
1541
+ "rstrip": false,
1542
+ "normalized": false,
1543
+ "special": true
1544
+ },
1545
+ {
1546
+ "id": 244,
1547
+ "content": "<|unused099|>",
1548
+ "single_word": false,
1549
+ "lstrip": false,
1550
+ "rstrip": false,
1551
+ "normalized": false,
1552
+ "special": true
1553
+ },
1554
+ {
1555
+ "id": 245,
1556
+ "content": "<|unused100|>",
1557
+ "single_word": false,
1558
+ "lstrip": false,
1559
+ "rstrip": false,
1560
+ "normalized": false,
1561
+ "special": true
1562
+ },
1563
+ {
1564
+ "id": 246,
1565
+ "content": "<|unused101|>",
1566
+ "single_word": false,
1567
+ "lstrip": false,
1568
+ "rstrip": false,
1569
+ "normalized": false,
1570
+ "special": true
1571
+ },
1572
+ {
1573
+ "id": 247,
1574
+ "content": "<|unused102|>",
1575
+ "single_word": false,
1576
+ "lstrip": false,
1577
+ "rstrip": false,
1578
+ "normalized": false,
1579
+ "special": true
1580
+ },
1581
+ {
1582
+ "id": 248,
1583
+ "content": "<|unused103|>",
1584
+ "single_word": false,
1585
+ "lstrip": false,
1586
+ "rstrip": false,
1587
+ "normalized": false,
1588
+ "special": true
1589
+ },
1590
+ {
1591
+ "id": 249,
1592
+ "content": "<|unused104|>",
1593
+ "single_word": false,
1594
+ "lstrip": false,
1595
+ "rstrip": false,
1596
+ "normalized": false,
1597
+ "special": true
1598
+ },
1599
+ {
1600
+ "id": 250,
1601
+ "content": "<|unused105|>",
1602
+ "single_word": false,
1603
+ "lstrip": false,
1604
+ "rstrip": false,
1605
+ "normalized": false,
1606
+ "special": true
1607
+ },
1608
+ {
1609
+ "id": 251,
1610
+ "content": "<|unused106|>",
1611
+ "single_word": false,
1612
+ "lstrip": false,
1613
+ "rstrip": false,
1614
+ "normalized": false,
1615
+ "special": true
1616
+ },
1617
+ {
1618
+ "id": 252,
1619
+ "content": "<|unused107|>",
1620
+ "single_word": false,
1621
+ "lstrip": false,
1622
+ "rstrip": false,
1623
+ "normalized": false,
1624
+ "special": true
1625
+ },
1626
+ {
1627
+ "id": 253,
1628
+ "content": "<|unused108|>",
1629
+ "single_word": false,
1630
+ "lstrip": false,
1631
+ "rstrip": false,
1632
+ "normalized": false,
1633
+ "special": true
1634
+ },
1635
+ {
1636
+ "id": 254,
1637
+ "content": "<|unused109|>",
1638
+ "single_word": false,
1639
+ "lstrip": false,
1640
+ "rstrip": false,
1641
+ "normalized": false,
1642
+ "special": true
1643
+ },
1644
+ {
1645
+ "id": 255,
1646
+ "content": "<|unused110|>",
1647
+ "single_word": false,
1648
+ "lstrip": false,
1649
+ "rstrip": false,
1650
+ "normalized": false,
1651
+ "special": true
1652
+ },
1653
+ {
1654
+ "id": 256,
1655
+ "content": "<|unused111|>",
1656
+ "single_word": false,
1657
+ "lstrip": false,
1658
+ "rstrip": false,
1659
+ "normalized": false,
1660
+ "special": true
1661
+ },
1662
+ {
1663
+ "id": 257,
1664
+ "content": "<|unused112|>",
1665
+ "single_word": false,
1666
+ "lstrip": false,
1667
+ "rstrip": false,
1668
+ "normalized": false,
1669
+ "special": true
1670
+ },
1671
+ {
1672
+ "id": 258,
1673
+ "content": "<|unused113|>",
1674
+ "single_word": false,
1675
+ "lstrip": false,
1676
+ "rstrip": false,
1677
+ "normalized": false,
1678
+ "special": true
1679
+ },
1680
+ {
1681
+ "id": 259,
1682
+ "content": "<|unused114|>",
1683
+ "single_word": false,
1684
+ "lstrip": false,
1685
+ "rstrip": false,
1686
+ "normalized": false,
1687
+ "special": true
1688
+ },
1689
+ {
1690
+ "id": 260,
1691
+ "content": "<|unused115|>",
1692
+ "single_word": false,
1693
+ "lstrip": false,
1694
+ "rstrip": false,
1695
+ "normalized": false,
1696
+ "special": true
1697
+ },
1698
+ {
1699
+ "id": 261,
1700
+ "content": "<|unused116|>",
1701
+ "single_word": false,
1702
+ "lstrip": false,
1703
+ "rstrip": false,
1704
+ "normalized": false,
1705
+ "special": true
1706
+ },
1707
+ {
1708
+ "id": 262,
1709
+ "content": "<|unused117|>",
1710
+ "single_word": false,
1711
+ "lstrip": false,
1712
+ "rstrip": false,
1713
+ "normalized": false,
1714
+ "special": true
1715
+ },
1716
+ {
1717
+ "id": 263,
1718
+ "content": "<|unused118|>",
1719
+ "single_word": false,
1720
+ "lstrip": false,
1721
+ "rstrip": false,
1722
+ "normalized": false,
1723
+ "special": true
1724
+ },
1725
+ {
1726
+ "id": 264,
1727
+ "content": "<|unused119|>",
1728
+ "single_word": false,
1729
+ "lstrip": false,
1730
+ "rstrip": false,
1731
+ "normalized": false,
1732
+ "special": true
1733
+ },
1734
+ {
1735
+ "id": 265,
1736
+ "content": "<|unused120|>",
1737
+ "single_word": false,
1738
+ "lstrip": false,
1739
+ "rstrip": false,
1740
+ "normalized": false,
1741
+ "special": true
1742
+ },
1743
+ {
1744
+ "id": 266,
1745
+ "content": "<|unused121|>",
1746
+ "single_word": false,
1747
+ "lstrip": false,
1748
+ "rstrip": false,
1749
+ "normalized": false,
1750
+ "special": true
1751
+ },
1752
+ {
1753
+ "id": 267,
1754
+ "content": "<|unused122|>",
1755
+ "single_word": false,
1756
+ "lstrip": false,
1757
+ "rstrip": false,
1758
+ "normalized": false,
1759
+ "special": true
1760
+ },
1761
+ {
1762
+ "id": 268,
1763
+ "content": "<|unused123|>",
1764
+ "single_word": false,
1765
+ "lstrip": false,
1766
+ "rstrip": false,
1767
+ "normalized": false,
1768
+ "special": true
1769
+ },
1770
+ {
1771
+ "id": 269,
1772
+ "content": "<|unused124|>",
1773
+ "single_word": false,
1774
+ "lstrip": false,
1775
+ "rstrip": false,
1776
+ "normalized": false,
1777
+ "special": true
1778
+ },
1779
+ {
1780
+ "id": 270,
1781
+ "content": "<|unused125|>",
1782
+ "single_word": false,
1783
+ "lstrip": false,
1784
+ "rstrip": false,
1785
+ "normalized": false,
1786
+ "special": true
1787
+ },
1788
+ {
1789
+ "id": 271,
1790
+ "content": "<|unused126|>",
1791
+ "single_word": false,
1792
+ "lstrip": false,
1793
+ "rstrip": false,
1794
+ "normalized": false,
1795
+ "special": true
1796
+ },
1797
+ {
1798
+ "id": 272,
1799
+ "content": "<|unused127|>",
1800
+ "single_word": false,
1801
+ "lstrip": false,
1802
+ "rstrip": false,
1803
+ "normalized": false,
1804
+ "special": true
1805
+ },
1806
+ {
1807
+ "id": 273,
1808
+ "content": "<|unused128|>",
1809
+ "single_word": false,
1810
+ "lstrip": false,
1811
+ "rstrip": false,
1812
+ "normalized": false,
1813
+ "special": true
1814
+ },
1815
+ {
1816
+ "id": 274,
1817
+ "content": "<|unused129|>",
1818
+ "single_word": false,
1819
+ "lstrip": false,
1820
+ "rstrip": false,
1821
+ "normalized": false,
1822
+ "special": true
1823
+ },
1824
+ {
1825
+ "id": 275,
1826
+ "content": "<|unused130|>",
1827
+ "single_word": false,
1828
+ "lstrip": false,
1829
+ "rstrip": false,
1830
+ "normalized": false,
1831
+ "special": true
1832
+ },
1833
+ {
1834
+ "id": 276,
1835
+ "content": "<|unused131|>",
1836
+ "single_word": false,
1837
+ "lstrip": false,
1838
+ "rstrip": false,
1839
+ "normalized": false,
1840
+ "special": true
1841
+ },
1842
+ {
1843
+ "id": 277,
1844
+ "content": "<|unused132|>",
1845
+ "single_word": false,
1846
+ "lstrip": false,
1847
+ "rstrip": false,
1848
+ "normalized": false,
1849
+ "special": true
1850
+ },
1851
+ {
1852
+ "id": 278,
1853
+ "content": "<|unused133|>",
1854
+ "single_word": false,
1855
+ "lstrip": false,
1856
+ "rstrip": false,
1857
+ "normalized": false,
1858
+ "special": true
1859
+ },
1860
+ {
1861
+ "id": 279,
1862
+ "content": "<|unused134|>",
1863
+ "single_word": false,
1864
+ "lstrip": false,
1865
+ "rstrip": false,
1866
+ "normalized": false,
1867
+ "special": true
1868
+ },
1869
+ {
1870
+ "id": 280,
1871
+ "content": "<|unused135|>",
1872
+ "single_word": false,
1873
+ "lstrip": false,
1874
+ "rstrip": false,
1875
+ "normalized": false,
1876
+ "special": true
1877
+ },
1878
+ {
1879
+ "id": 281,
1880
+ "content": "<|unused136|>",
1881
+ "single_word": false,
1882
+ "lstrip": false,
1883
+ "rstrip": false,
1884
+ "normalized": false,
1885
+ "special": true
1886
+ },
1887
+ {
1888
+ "id": 282,
1889
+ "content": "<|unused137|>",
1890
+ "single_word": false,
1891
+ "lstrip": false,
1892
+ "rstrip": false,
1893
+ "normalized": false,
1894
+ "special": true
1895
+ },
1896
+ {
1897
+ "id": 283,
1898
+ "content": "<|unused138|>",
1899
+ "single_word": false,
1900
+ "lstrip": false,
1901
+ "rstrip": false,
1902
+ "normalized": false,
1903
+ "special": true
1904
+ },
1905
+ {
1906
+ "id": 284,
1907
+ "content": "<|unused139|>",
1908
+ "single_word": false,
1909
+ "lstrip": false,
1910
+ "rstrip": false,
1911
+ "normalized": false,
1912
+ "special": true
1913
+ },
1914
+ {
1915
+ "id": 285,
1916
+ "content": "<|unused140|>",
1917
+ "single_word": false,
1918
+ "lstrip": false,
1919
+ "rstrip": false,
1920
+ "normalized": false,
1921
+ "special": true
1922
+ },
1923
+ {
1924
+ "id": 286,
1925
+ "content": "<|unused141|>",
1926
+ "single_word": false,
1927
+ "lstrip": false,
1928
+ "rstrip": false,
1929
+ "normalized": false,
1930
+ "special": true
1931
+ },
1932
+ {
1933
+ "id": 287,
1934
+ "content": "<|unused142|>",
1935
+ "single_word": false,
1936
+ "lstrip": false,
1937
+ "rstrip": false,
1938
+ "normalized": false,
1939
+ "special": true
1940
+ },
1941
+ {
1942
+ "id": 288,
1943
+ "content": "<|unused143|>",
1944
+ "single_word": false,
1945
+ "lstrip": false,
1946
+ "rstrip": false,
1947
+ "normalized": false,
1948
+ "special": true
1949
+ },
1950
+ {
1951
+ "id": 289,
1952
+ "content": "<|unused144|>",
1953
+ "single_word": false,
1954
+ "lstrip": false,
1955
+ "rstrip": false,
1956
+ "normalized": false,
1957
+ "special": true
1958
+ },
1959
+ {
1960
+ "id": 290,
1961
+ "content": "<|unused145|>",
1962
+ "single_word": false,
1963
+ "lstrip": false,
1964
+ "rstrip": false,
1965
+ "normalized": false,
1966
+ "special": true
1967
+ },
1968
+ {
1969
+ "id": 291,
1970
+ "content": "<|unused146|>",
1971
+ "single_word": false,
1972
+ "lstrip": false,
1973
+ "rstrip": false,
1974
+ "normalized": false,
1975
+ "special": true
1976
+ },
1977
+ {
1978
+ "id": 292,
1979
+ "content": "<|unused147|>",
1980
+ "single_word": false,
1981
+ "lstrip": false,
1982
+ "rstrip": false,
1983
+ "normalized": false,
1984
+ "special": true
1985
+ },
1986
+ {
1987
+ "id": 293,
1988
+ "content": "<|unused148|>",
1989
+ "single_word": false,
1990
+ "lstrip": false,
1991
+ "rstrip": false,
1992
+ "normalized": false,
1993
+ "special": true
1994
+ },
1995
+ {
1996
+ "id": 294,
1997
+ "content": "<|unused149|>",
1998
+ "single_word": false,
1999
+ "lstrip": false,
2000
+ "rstrip": false,
2001
+ "normalized": false,
2002
+ "special": true
2003
+ },
2004
+ {
2005
+ "id": 295,
2006
+ "content": "<|unused150|>",
2007
+ "single_word": false,
2008
+ "lstrip": false,
2009
+ "rstrip": false,
2010
+ "normalized": false,
2011
+ "special": true
2012
+ },
2013
+ {
2014
+ "id": 296,
2015
+ "content": "<|unused151|>",
2016
+ "single_word": false,
2017
+ "lstrip": false,
2018
+ "rstrip": false,
2019
+ "normalized": false,
2020
+ "special": true
2021
+ },
2022
+ {
2023
+ "id": 297,
2024
+ "content": "<|unused152|>",
2025
+ "single_word": false,
2026
+ "lstrip": false,
2027
+ "rstrip": false,
2028
+ "normalized": false,
2029
+ "special": true
2030
+ },
2031
+ {
2032
+ "id": 298,
2033
+ "content": "<|unused153|>",
2034
+ "single_word": false,
2035
+ "lstrip": false,
2036
+ "rstrip": false,
2037
+ "normalized": false,
2038
+ "special": true
2039
+ },
2040
+ {
2041
+ "id": 299,
2042
+ "content": "<|unused154|>",
2043
+ "single_word": false,
2044
+ "lstrip": false,
2045
+ "rstrip": false,
2046
+ "normalized": false,
2047
+ "special": true
2048
+ },
2049
+ {
2050
+ "id": 300,
2051
+ "content": "<|unused155|>",
2052
+ "single_word": false,
2053
+ "lstrip": false,
2054
+ "rstrip": false,
2055
+ "normalized": false,
2056
+ "special": true
2057
+ },
2058
+ {
2059
+ "id": 301,
2060
+ "content": "<|unused156|>",
2061
+ "single_word": false,
2062
+ "lstrip": false,
2063
+ "rstrip": false,
2064
+ "normalized": false,
2065
+ "special": true
2066
+ },
2067
+ {
2068
+ "id": 302,
2069
+ "content": "<|unused157|>",
2070
+ "single_word": false,
2071
+ "lstrip": false,
2072
+ "rstrip": false,
2073
+ "normalized": false,
2074
+ "special": true
2075
+ },
2076
+ {
2077
+ "id": 303,
2078
+ "content": "<|unused158|>",
2079
+ "single_word": false,
2080
+ "lstrip": false,
2081
+ "rstrip": false,
2082
+ "normalized": false,
2083
+ "special": true
2084
+ },
2085
+ {
2086
+ "id": 304,
2087
+ "content": "<|unused159|>",
2088
+ "single_word": false,
2089
+ "lstrip": false,
2090
+ "rstrip": false,
2091
+ "normalized": false,
2092
+ "special": true
2093
  }
2094
  ],
2095
  "normalizer": {
 
2121
  },
2122
  {
2123
  "type": "Fuse"
2124
+ },
2125
+ {
2126
+ "type": "Strip",
2127
+ "content": " ",
2128
+ "start": 1,
2129
+ "stop": 0
2130
  }
2131
  ]
2132
  },
 
2142
  "<unk>": 0,
2143
  "<|startoftext|>": 1,
2144
  "<|endoftext|>": 2,
 
 
 
2145
  "<|im_start|>": 6,
2146
  "<|im_end|>": 7,
2147
  "<|im_sep|>": 8,
 
 
 
 
 
2148
  "<fim_prefix>": 14,
2149
  "<fim_middle>": 15,
2150
  "<fim_suffix>": 16,
 
176164
  "现 今"
176165
  ]
176166
  }
176167
+ }