KoichiYasuoka commited on
Commit
3f9f094
·
1 Parent(s): 0fefe30

initial release

Browse files
Files changed (9) hide show
  1. README.md +30 -0
  2. config.json +533 -0
  3. lfm2.py +5 -0
  4. maker.py +115 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +23 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +4079 -0
  9. ud.py +166 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "ja"
4
+ tags:
5
+ - "japanese"
6
+ - "pos"
7
+ - "dependency-parsing"
8
+ base_model: LiquidAI/LFM2-350M
9
+ datasets:
10
+ - "universal_dependencies"
11
+ license: "lfm1.0"
12
+ pipeline_tag: "token-classification"
13
+ widget:
14
+ - text: "全学年にわたって小学校の国語の教科書に挿し絵が用いられている"
15
+ ---
16
+
17
+ # lfm2-350m-japanese-ud-embeds
18
+
19
+ ## Model Description
20
+
21
+ This is a LFM2 model pretrained for POS-tagging and dependency-parsing, derived from [LFM2-350M](https://huggingface.co/LiquidAI/LFM2-350M) and [UD_Japanese-GSDLUW](https://github.com/UniversalDependencies/UD_Japanese-GSDLUW).
22
+
23
+ ## How to Use
24
+
25
+ ```
26
+ from transformers import pipeline
27
+ nlp=pipeline("universal-dependencies","KoichiYasuoka/lfm2-350m-japanese-ud-embeds",trust_remote_code=True)
28
+ print(nlp("全学年にわたって小学校の国語の教科書に挿し絵が用いられている"))
29
+ ```
30
+
config.json ADDED
@@ -0,0 +1,533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForTokenClassification"
4
+ ],
5
+ "auto_map": {
6
+ "AutoModelForTokenClassification": "lfm2.Lfm2ForTokenClassification"
7
+ },
8
+ "block_auto_adjust_ff_dim": true,
9
+ "block_dim": 1024,
10
+ "block_ff_dim": 6656,
11
+ "block_ffn_dim_multiplier": 1.0,
12
+ "block_mlp_init_scale": 1.0,
13
+ "block_multiple_of": 256,
14
+ "block_norm_eps": 1e-05,
15
+ "block_out_init_scale": 1.0,
16
+ "block_use_swiglu": true,
17
+ "block_use_xavier_init": true,
18
+ "bos_token_id": 1,
19
+ "conv_L_cache": 3,
20
+ "conv_bias": false,
21
+ "conv_dim": 1024,
22
+ "conv_dim_out": 1024,
23
+ "conv_use_xavier_init": true,
24
+ "custom_pipelines": {
25
+ "upos": {
26
+ "impl": "ud.BellmanFordTokenClassificationPipeline",
27
+ "pt": "AutoModelForTokenClassification"
28
+ },
29
+ "universal-dependencies": {
30
+ "impl": "ud.UniversalDependenciesPipeline",
31
+ "pt": "AutoModelForTokenClassification"
32
+ }
33
+ },
34
+ "eos_token_id": 7,
35
+ "hidden_size": 1024,
36
+ "id2label": {
37
+ "0": "ADJ",
38
+ "1": "ADJ.",
39
+ "2": "ADJ|_",
40
+ "3": "ADJ|l-acl",
41
+ "4": "ADJ|l-advcl",
42
+ "5": "ADJ|l-amod",
43
+ "6": "ADJ|l-ccomp",
44
+ "7": "ADJ|l-csubj",
45
+ "8": "ADJ|l-csubj:outer",
46
+ "9": "ADJ|l-nmod",
47
+ "10": "ADJ|l-nsubj",
48
+ "11": "ADJ|l-obj",
49
+ "12": "ADJ|l-obl",
50
+ "13": "ADJ|r-acl",
51
+ "14": "ADJ|r-amod",
52
+ "15": "ADJ|r-dep",
53
+ "16": "ADJ|root",
54
+ "17": "ADP",
55
+ "18": "ADP.",
56
+ "19": "ADP|_",
57
+ "20": "ADP|l-case",
58
+ "21": "ADP|r-case",
59
+ "22": "ADP|r-fixed",
60
+ "23": "ADV",
61
+ "24": "ADV.",
62
+ "25": "ADV|_",
63
+ "26": "ADV|l-advcl",
64
+ "27": "ADV|l-advmod",
65
+ "28": "ADV|l-obj",
66
+ "29": "ADV|r-dep",
67
+ "30": "ADV|root",
68
+ "31": "AUX",
69
+ "32": "AUX.",
70
+ "33": "AUX|Polarity=Neg|_",
71
+ "34": "AUX|Polarity=Neg|r-aux",
72
+ "35": "AUX|Polarity=Neg|r-fixed",
73
+ "36": "AUX|_",
74
+ "37": "AUX|r-aux",
75
+ "38": "AUX|r-cop",
76
+ "39": "AUX|r-fixed",
77
+ "40": "AUX|root",
78
+ "41": "B-ADJ",
79
+ "42": "B-ADJ.",
80
+ "43": "B-ADP",
81
+ "44": "B-ADP.",
82
+ "45": "B-ADV",
83
+ "46": "B-ADV.",
84
+ "47": "B-AUX",
85
+ "48": "B-AUX.",
86
+ "49": "B-CCONJ",
87
+ "50": "B-CCONJ.",
88
+ "51": "B-DET",
89
+ "52": "B-DET.",
90
+ "53": "B-INTJ",
91
+ "54": "B-INTJ.",
92
+ "55": "B-NOUN",
93
+ "56": "B-NOUN.",
94
+ "57": "B-NUM",
95
+ "58": "B-NUM.",
96
+ "59": "B-PART",
97
+ "60": "B-PART.",
98
+ "61": "B-PRON",
99
+ "62": "B-PRON.",
100
+ "63": "B-PROPN",
101
+ "64": "B-PROPN.",
102
+ "65": "B-PUNCT",
103
+ "66": "B-PUNCT.",
104
+ "67": "B-SCONJ",
105
+ "68": "B-SCONJ.",
106
+ "69": "B-SYM",
107
+ "70": "B-SYM.",
108
+ "71": "B-VERB",
109
+ "72": "B-VERB.",
110
+ "73": "B-X",
111
+ "74": "B-X.",
112
+ "75": "CCONJ",
113
+ "76": "CCONJ.",
114
+ "77": "CCONJ|_",
115
+ "78": "CCONJ|l-cc",
116
+ "79": "CCONJ|r-cc",
117
+ "80": "DET",
118
+ "81": "DET.",
119
+ "82": "DET|_",
120
+ "83": "DET|l-det",
121
+ "84": "I-ADJ",
122
+ "85": "I-ADJ.",
123
+ "86": "I-ADP",
124
+ "87": "I-ADP.",
125
+ "88": "I-ADV",
126
+ "89": "I-ADV.",
127
+ "90": "I-AUX",
128
+ "91": "I-AUX.",
129
+ "92": "I-CCONJ",
130
+ "93": "I-CCONJ.",
131
+ "94": "I-DET",
132
+ "95": "I-DET.",
133
+ "96": "I-INTJ",
134
+ "97": "I-INTJ.",
135
+ "98": "I-NOUN",
136
+ "99": "I-NOUN.",
137
+ "100": "I-NUM",
138
+ "101": "I-NUM.",
139
+ "102": "I-PART",
140
+ "103": "I-PART.",
141
+ "104": "I-PRON",
142
+ "105": "I-PRON.",
143
+ "106": "I-PROPN",
144
+ "107": "I-PROPN.",
145
+ "108": "I-PUNCT",
146
+ "109": "I-PUNCT.",
147
+ "110": "I-SCONJ",
148
+ "111": "I-SCONJ.",
149
+ "112": "I-SYM",
150
+ "113": "I-SYM.",
151
+ "114": "I-VERB",
152
+ "115": "I-VERB.",
153
+ "116": "I-X",
154
+ "117": "I-X.",
155
+ "118": "INTJ",
156
+ "119": "INTJ.",
157
+ "120": "INTJ|_",
158
+ "121": "INTJ|l-discourse",
159
+ "122": "INTJ|r-discourse",
160
+ "123": "INTJ|root",
161
+ "124": "NOUN",
162
+ "125": "NOUN.",
163
+ "126": "NOUN|Polarity=Neg|_",
164
+ "127": "NOUN|Polarity=Neg|l-obl",
165
+ "128": "NOUN|Polarity=Neg|root",
166
+ "129": "NOUN|_",
167
+ "130": "NOUN|l-acl",
168
+ "131": "NOUN|l-advcl",
169
+ "132": "NOUN|l-ccomp",
170
+ "133": "NOUN|l-compound",
171
+ "134": "NOUN|l-csubj",
172
+ "135": "NOUN|l-csubj:outer",
173
+ "136": "NOUN|l-nmod",
174
+ "137": "NOUN|l-nsubj",
175
+ "138": "NOUN|l-nsubj:outer",
176
+ "139": "NOUN|l-obj",
177
+ "140": "NOUN|l-obl",
178
+ "141": "NOUN|r-compound",
179
+ "142": "NOUN|r-nmod",
180
+ "143": "NOUN|r-nsubj",
181
+ "144": "NOUN|root",
182
+ "145": "NUM",
183
+ "146": "NUM.",
184
+ "147": "NUM|_",
185
+ "148": "NUM|l-advcl",
186
+ "149": "NUM|l-compound",
187
+ "150": "NUM|l-nmod",
188
+ "151": "NUM|l-nsubj",
189
+ "152": "NUM|l-nsubj:outer",
190
+ "153": "NUM|l-nummod",
191
+ "154": "NUM|l-obj",
192
+ "155": "NUM|l-obl",
193
+ "156": "NUM|r-compound",
194
+ "157": "NUM|root",
195
+ "158": "PART",
196
+ "159": "PART.",
197
+ "160": "PART|_",
198
+ "161": "PART|l-mark",
199
+ "162": "PART|r-mark",
200
+ "163": "PRON",
201
+ "164": "PRON.",
202
+ "165": "PRON|_",
203
+ "166": "PRON|l-acl",
204
+ "167": "PRON|l-advcl",
205
+ "168": "PRON|l-nmod",
206
+ "169": "PRON|l-nsubj",
207
+ "170": "PRON|l-nsubj:outer",
208
+ "171": "PRON|l-obj",
209
+ "172": "PRON|l-obl",
210
+ "173": "PRON|root",
211
+ "174": "PROPN",
212
+ "175": "PROPN.",
213
+ "176": "PROPN|_",
214
+ "177": "PROPN|l-acl",
215
+ "178": "PROPN|l-advcl",
216
+ "179": "PROPN|l-compound",
217
+ "180": "PROPN|l-nmod",
218
+ "181": "PROPN|l-nsubj",
219
+ "182": "PROPN|l-nsubj:outer",
220
+ "183": "PROPN|l-obj",
221
+ "184": "PROPN|l-obl",
222
+ "185": "PROPN|r-compound",
223
+ "186": "PROPN|r-nmod",
224
+ "187": "PROPN|root",
225
+ "188": "PUNCT",
226
+ "189": "PUNCT.",
227
+ "190": "PUNCT|_",
228
+ "191": "PUNCT|l-punct",
229
+ "192": "PUNCT|r-punct",
230
+ "193": "SCONJ",
231
+ "194": "SCONJ.",
232
+ "195": "SCONJ|_",
233
+ "196": "SCONJ|l-dep",
234
+ "197": "SCONJ|r-fixed",
235
+ "198": "SCONJ|r-mark",
236
+ "199": "SYM",
237
+ "200": "SYM.",
238
+ "201": "SYM|_",
239
+ "202": "SYM|l-compound",
240
+ "203": "SYM|l-dep",
241
+ "204": "SYM|l-nmod",
242
+ "205": "SYM|l-obl",
243
+ "206": "SYM|r-compound",
244
+ "207": "SYM|r-dep",
245
+ "208": "VERB",
246
+ "209": "VERB.",
247
+ "210": "VERB|_",
248
+ "211": "VERB|l-acl",
249
+ "212": "VERB|l-advcl",
250
+ "213": "VERB|l-ccomp",
251
+ "214": "VERB|l-compound",
252
+ "215": "VERB|l-csubj",
253
+ "216": "VERB|l-csubj:outer",
254
+ "217": "VERB|l-nmod",
255
+ "218": "VERB|l-obj",
256
+ "219": "VERB|l-obl",
257
+ "220": "VERB|r-acl",
258
+ "221": "VERB|r-advcl",
259
+ "222": "VERB|r-compound",
260
+ "223": "VERB|root",
261
+ "224": "X",
262
+ "225": "X.",
263
+ "226": "X|_",
264
+ "227": "X|l-nmod",
265
+ "228": "X|r-dep"
266
+ },
267
+ "initializer_range": 0.02,
268
+ "intermediate_size": 6656,
269
+ "label2id": {
270
+ "ADJ": 0,
271
+ "ADJ.": 1,
272
+ "ADJ|_": 2,
273
+ "ADJ|l-acl": 3,
274
+ "ADJ|l-advcl": 4,
275
+ "ADJ|l-amod": 5,
276
+ "ADJ|l-ccomp": 6,
277
+ "ADJ|l-csubj": 7,
278
+ "ADJ|l-csubj:outer": 8,
279
+ "ADJ|l-nmod": 9,
280
+ "ADJ|l-nsubj": 10,
281
+ "ADJ|l-obj": 11,
282
+ "ADJ|l-obl": 12,
283
+ "ADJ|r-acl": 13,
284
+ "ADJ|r-amod": 14,
285
+ "ADJ|r-dep": 15,
286
+ "ADJ|root": 16,
287
+ "ADP": 17,
288
+ "ADP.": 18,
289
+ "ADP|_": 19,
290
+ "ADP|l-case": 20,
291
+ "ADP|r-case": 21,
292
+ "ADP|r-fixed": 22,
293
+ "ADV": 23,
294
+ "ADV.": 24,
295
+ "ADV|_": 25,
296
+ "ADV|l-advcl": 26,
297
+ "ADV|l-advmod": 27,
298
+ "ADV|l-obj": 28,
299
+ "ADV|r-dep": 29,
300
+ "ADV|root": 30,
301
+ "AUX": 31,
302
+ "AUX.": 32,
303
+ "AUX|Polarity=Neg|_": 33,
304
+ "AUX|Polarity=Neg|r-aux": 34,
305
+ "AUX|Polarity=Neg|r-fixed": 35,
306
+ "AUX|_": 36,
307
+ "AUX|r-aux": 37,
308
+ "AUX|r-cop": 38,
309
+ "AUX|r-fixed": 39,
310
+ "AUX|root": 40,
311
+ "B-ADJ": 41,
312
+ "B-ADJ.": 42,
313
+ "B-ADP": 43,
314
+ "B-ADP.": 44,
315
+ "B-ADV": 45,
316
+ "B-ADV.": 46,
317
+ "B-AUX": 47,
318
+ "B-AUX.": 48,
319
+ "B-CCONJ": 49,
320
+ "B-CCONJ.": 50,
321
+ "B-DET": 51,
322
+ "B-DET.": 52,
323
+ "B-INTJ": 53,
324
+ "B-INTJ.": 54,
325
+ "B-NOUN": 55,
326
+ "B-NOUN.": 56,
327
+ "B-NUM": 57,
328
+ "B-NUM.": 58,
329
+ "B-PART": 59,
330
+ "B-PART.": 60,
331
+ "B-PRON": 61,
332
+ "B-PRON.": 62,
333
+ "B-PROPN": 63,
334
+ "B-PROPN.": 64,
335
+ "B-PUNCT": 65,
336
+ "B-PUNCT.": 66,
337
+ "B-SCONJ": 67,
338
+ "B-SCONJ.": 68,
339
+ "B-SYM": 69,
340
+ "B-SYM.": 70,
341
+ "B-VERB": 71,
342
+ "B-VERB.": 72,
343
+ "B-X": 73,
344
+ "B-X.": 74,
345
+ "CCONJ": 75,
346
+ "CCONJ.": 76,
347
+ "CCONJ|_": 77,
348
+ "CCONJ|l-cc": 78,
349
+ "CCONJ|r-cc": 79,
350
+ "DET": 80,
351
+ "DET.": 81,
352
+ "DET|_": 82,
353
+ "DET|l-det": 83,
354
+ "I-ADJ": 84,
355
+ "I-ADJ.": 85,
356
+ "I-ADP": 86,
357
+ "I-ADP.": 87,
358
+ "I-ADV": 88,
359
+ "I-ADV.": 89,
360
+ "I-AUX": 90,
361
+ "I-AUX.": 91,
362
+ "I-CCONJ": 92,
363
+ "I-CCONJ.": 93,
364
+ "I-DET": 94,
365
+ "I-DET.": 95,
366
+ "I-INTJ": 96,
367
+ "I-INTJ.": 97,
368
+ "I-NOUN": 98,
369
+ "I-NOUN.": 99,
370
+ "I-NUM": 100,
371
+ "I-NUM.": 101,
372
+ "I-PART": 102,
373
+ "I-PART.": 103,
374
+ "I-PRON": 104,
375
+ "I-PRON.": 105,
376
+ "I-PROPN": 106,
377
+ "I-PROPN.": 107,
378
+ "I-PUNCT": 108,
379
+ "I-PUNCT.": 109,
380
+ "I-SCONJ": 110,
381
+ "I-SCONJ.": 111,
382
+ "I-SYM": 112,
383
+ "I-SYM.": 113,
384
+ "I-VERB": 114,
385
+ "I-VERB.": 115,
386
+ "I-X": 116,
387
+ "I-X.": 117,
388
+ "INTJ": 118,
389
+ "INTJ.": 119,
390
+ "INTJ|_": 120,
391
+ "INTJ|l-discourse": 121,
392
+ "INTJ|r-discourse": 122,
393
+ "INTJ|root": 123,
394
+ "NOUN": 124,
395
+ "NOUN.": 125,
396
+ "NOUN|Polarity=Neg|_": 126,
397
+ "NOUN|Polarity=Neg|l-obl": 127,
398
+ "NOUN|Polarity=Neg|root": 128,
399
+ "NOUN|_": 129,
400
+ "NOUN|l-acl": 130,
401
+ "NOUN|l-advcl": 131,
402
+ "NOUN|l-ccomp": 132,
403
+ "NOUN|l-compound": 133,
404
+ "NOUN|l-csubj": 134,
405
+ "NOUN|l-csubj:outer": 135,
406
+ "NOUN|l-nmod": 136,
407
+ "NOUN|l-nsubj": 137,
408
+ "NOUN|l-nsubj:outer": 138,
409
+ "NOUN|l-obj": 139,
410
+ "NOUN|l-obl": 140,
411
+ "NOUN|r-compound": 141,
412
+ "NOUN|r-nmod": 142,
413
+ "NOUN|r-nsubj": 143,
414
+ "NOUN|root": 144,
415
+ "NUM": 145,
416
+ "NUM.": 146,
417
+ "NUM|_": 147,
418
+ "NUM|l-advcl": 148,
419
+ "NUM|l-compound": 149,
420
+ "NUM|l-nmod": 150,
421
+ "NUM|l-nsubj": 151,
422
+ "NUM|l-nsubj:outer": 152,
423
+ "NUM|l-nummod": 153,
424
+ "NUM|l-obj": 154,
425
+ "NUM|l-obl": 155,
426
+ "NUM|r-compound": 156,
427
+ "NUM|root": 157,
428
+ "PART": 158,
429
+ "PART.": 159,
430
+ "PART|_": 160,
431
+ "PART|l-mark": 161,
432
+ "PART|r-mark": 162,
433
+ "PRON": 163,
434
+ "PRON.": 164,
435
+ "PRON|_": 165,
436
+ "PRON|l-acl": 166,
437
+ "PRON|l-advcl": 167,
438
+ "PRON|l-nmod": 168,
439
+ "PRON|l-nsubj": 169,
440
+ "PRON|l-nsubj:outer": 170,
441
+ "PRON|l-obj": 171,
442
+ "PRON|l-obl": 172,
443
+ "PRON|root": 173,
444
+ "PROPN": 174,
445
+ "PROPN.": 175,
446
+ "PROPN|_": 176,
447
+ "PROPN|l-acl": 177,
448
+ "PROPN|l-advcl": 178,
449
+ "PROPN|l-compound": 179,
450
+ "PROPN|l-nmod": 180,
451
+ "PROPN|l-nsubj": 181,
452
+ "PROPN|l-nsubj:outer": 182,
453
+ "PROPN|l-obj": 183,
454
+ "PROPN|l-obl": 184,
455
+ "PROPN|r-compound": 185,
456
+ "PROPN|r-nmod": 186,
457
+ "PROPN|root": 187,
458
+ "PUNCT": 188,
459
+ "PUNCT.": 189,
460
+ "PUNCT|_": 190,
461
+ "PUNCT|l-punct": 191,
462
+ "PUNCT|r-punct": 192,
463
+ "SCONJ": 193,
464
+ "SCONJ.": 194,
465
+ "SCONJ|_": 195,
466
+ "SCONJ|l-dep": 196,
467
+ "SCONJ|r-fixed": 197,
468
+ "SCONJ|r-mark": 198,
469
+ "SYM": 199,
470
+ "SYM.": 200,
471
+ "SYM|_": 201,
472
+ "SYM|l-compound": 202,
473
+ "SYM|l-dep": 203,
474
+ "SYM|l-nmod": 204,
475
+ "SYM|l-obl": 205,
476
+ "SYM|r-compound": 206,
477
+ "SYM|r-dep": 207,
478
+ "VERB": 208,
479
+ "VERB.": 209,
480
+ "VERB|_": 210,
481
+ "VERB|l-acl": 211,
482
+ "VERB|l-advcl": 212,
483
+ "VERB|l-ccomp": 213,
484
+ "VERB|l-compound": 214,
485
+ "VERB|l-csubj": 215,
486
+ "VERB|l-csubj:outer": 216,
487
+ "VERB|l-nmod": 217,
488
+ "VERB|l-obj": 218,
489
+ "VERB|l-obl": 219,
490
+ "VERB|r-acl": 220,
491
+ "VERB|r-advcl": 221,
492
+ "VERB|r-compound": 222,
493
+ "VERB|root": 223,
494
+ "X": 224,
495
+ "X.": 225,
496
+ "X|_": 226,
497
+ "X|l-nmod": 227,
498
+ "X|r-dep": 228
499
+ },
500
+ "layer_types": [
501
+ "conv",
502
+ "conv",
503
+ "full_attention",
504
+ "conv",
505
+ "conv",
506
+ "full_attention",
507
+ "conv",
508
+ "conv",
509
+ "full_attention",
510
+ "conv",
511
+ "full_attention",
512
+ "conv",
513
+ "full_attention",
514
+ "conv",
515
+ "full_attention",
516
+ "conv"
517
+ ],
518
+ "max_position_embeddings": 128000,
519
+ "model_type": "lfm2",
520
+ "norm_eps": 1e-05,
521
+ "num_attention_heads": 16,
522
+ "num_heads": 16,
523
+ "num_hidden_layers": 16,
524
+ "num_key_value_heads": 8,
525
+ "pad_token_id": 0,
526
+ "rope_theta": 1000000.0,
527
+ "tokenizer_class": "PreTrainedTokenizerFast",
528
+ "torch_dtype": "float32",
529
+ "transformers_version": "4.54.0",
530
+ "use_cache": true,
531
+ "use_pos_enc": true,
532
+ "vocab_size": 65536
533
+ }
lfm2.py ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ from transformers import Lfm2PreTrainedModel
2
+ from transformers.modeling_layers import GenericForTokenClassification
3
+
4
+ class Lfm2ForTokenClassification(GenericForTokenClassification,Lfm2PreTrainedModel):
5
+ pass
maker.py ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #! /usr/bin/python3
2
+ import os
3
+ src="LiquidAI/LFM2-350M"
4
+ tgt="KoichiYasuoka/lfm2-350m-japanese-ud-embeds"
5
+ url="https://github.com/UniversalDependencies/UD_Japanese-GSDLUW"
6
+ d=os.path.basename(url)
7
+ os.system(f"test -d {d} || git clone --depth=1 {url}")
8
+ os.system(f"for F in train dev test ; do cp {d}/*-$F.conllu $F.conllu ; done")
9
+ class UDEmbedsDataset(object):
10
+ def __init__(self,conllu,tokenizer,oldtokenizer=None,embeddings=None):
11
+ self.conllu=open(conllu,"r",encoding="utf-8")
12
+ self.tokenizer=tokenizer
13
+ self.oldtokenizer=oldtokenizer if oldtokenizer else tokenizer
14
+ self.embeddings=embeddings
15
+ self.seeks=[0]
16
+ label=set(["SYM","SYM.","SYM|_"])
17
+ dep=set()
18
+ s=self.conllu.readline()
19
+ while s!="":
20
+ if s=="\n":
21
+ self.seeks.append(self.conllu.tell())
22
+ else:
23
+ w=s.split("\t")
24
+ if len(w)==10:
25
+ if w[0].isdecimal():
26
+ p=w[3]
27
+ q="" if w[5]=="_" else "|"+w[5]
28
+ d=("|" if w[6]=="0" else "|l-" if int(w[0])<int(w[6]) else "|r-")+w[7]
29
+ for k in [p,p+".","B-"+p,"B-"+p+".","I-"+p,"I-"+p+".",p+q+"|_",p+q+d]:
30
+ label.add(k)
31
+ s=self.conllu.readline()
32
+ self.label2id={l:i for i,l in enumerate(sorted(label))}
33
+ def __call__(*args):
34
+ lid={l:i for i,l in enumerate(sorted(set(sum([list(t.label2id) for t in args],[]))))}
35
+ for t in args:
36
+ t.label2id=lid
37
+ return lid
38
+ def __del__(self):
39
+ self.conllu.close()
40
+ __len__=lambda self:len(self.seeks)-1
41
+ def __getitem__(self,i):
42
+ import torch
43
+ self.conllu.seek(self.seeks[i])
44
+ c,t,s=[],[""],False
45
+ while t[0]!="\n":
46
+ t=self.conllu.readline().split("\t")
47
+ if len(t)==10 and t[0].isdecimal():
48
+ if s:
49
+ t[1]=" "+t[1]
50
+ c.append(t)
51
+ s=t[9].find("SpaceAfter=No")<0
52
+ x=[True if t[6]=="0" or int(t[6])>j or sum([1 if int(c[i][6])==j+1 else 0 for i in range(j+1,len(c))])>0 else False for j,t in enumerate(c)]
53
+ v=self.tokenizer([t[1] for t in c],add_special_tokens=False)["input_ids"]
54
+ ids,upos=[self.tokenizer.bos_token_id],["SYM."]
55
+ for i,(j,k) in enumerate(zip(v,c)):
56
+ if j==[]:
57
+ j=[self.tokenizer.unk_token_id]
58
+ p=k[3] if x[i] else k[3]+"."
59
+ ids+=j
60
+ upos+=[p] if len(j)==1 else ["B-"+p]+["I-"+p]*(len(j)-1)
61
+ x=[True if t[6]=="0" or int(t[6])>j or sum([1 if int(c[i][6])==j+1 else 0 for i in range(j+1,len(c))])>0 else False for j,t in enumerate(c)]
62
+ if len(x)<504:
63
+ x=[True]*len(x)
64
+ else:
65
+ w=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+len(ids)+1
66
+ for i in range(len(x)):
67
+ if x[i]==False and w+len(x)-i<128000:
68
+ x[i]=True
69
+ w+=len(x)-i+1
70
+ v=self.oldtokenizer([t[1] for t in c],add_special_tokens=False)["input_ids"]
71
+ p=[t[3] if t[5]=="_" else t[3]+"|"+t[5] for i,t in enumerate(c)]
72
+ d=[t[7] if t[6]=="0" else "l-"+t[7] if int(t[0])<int(t[6]) else "r-"+t[7] for t in c]
73
+ idx=[-1]
74
+ upos.append("SYM|_")
75
+ for i in range(len(x)):
76
+ if x[i]:
77
+ idx.append(i)
78
+ upos.append(p[i]+"|"+d[i] if c[i][6]=="0" else p[i]+"|_")
79
+ for j in range(i+1,len(x)):
80
+ idx.append(j)
81
+ upos.append(p[j]+"|"+d[j] if int(c[j][6])==i+1 else p[i]+"|"+d[i] if int(c[i][6])==j+1 else p[j]+"|_")
82
+ idx.append(-1)
83
+ upos.append("SYM|_")
84
+ with torch.no_grad():
85
+ m=[]
86
+ for j in v:
87
+ if j==[]:
88
+ j=[self.tokenizer.unk_token_id]
89
+ m.append(self.embeddings[j,:].sum(axis=0))
90
+ m.append(self.embeddings[self.tokenizer.eos_token_id])
91
+ emb=torch.stack(m)
92
+ return{"inputs_embeds":torch.vstack((self.embeddings[ids,:],emb[idx,:])),"labels":[self.label2id[p] for p in upos]}
93
+ from transformers import AutoTokenizer,AutoConfig,Lfm2PreTrainedModel,DefaultDataCollator,TrainingArguments,Trainer
94
+ from transformers.modeling_layers import GenericForTokenClassification
95
+ class Lfm2ForTokenClassification(GenericForTokenClassification,Lfm2PreTrainedModel):
96
+ pass
97
+ from tokenizers.pre_tokenizers import Sequence,Split,Whitespace,Punctuation
98
+ from tokenizers import Regex
99
+ from copy import deepcopy
100
+ otk=AutoTokenizer.from_pretrained(src,unk_token="<|endoftext|>")
101
+ otk.model_input_names=["input_ids","attention_mask"]
102
+ ntk=deepcopy(otk)
103
+ ntk.backend_tokenizer.pre_tokenizer=Sequence([Split(Regex("[ぁ-ん]"),"isolated"),Whitespace(),Punctuation(),otk.backend_tokenizer.pre_tokenizer])
104
+ trainDS=UDEmbedsDataset("train.conllu",ntk,otk)
105
+ devDS=UDEmbedsDataset("dev.conllu",ntk,otk)
106
+ testDS=UDEmbedsDataset("test.conllu",ntk,otk)
107
+ lid=trainDS(devDS,testDS)
108
+ cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True,trust_remote_code=True)
109
+ mdl=Lfm2ForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True,trust_remote_code=True)
110
+ trainDS.embeddings=mdl.get_input_embeddings().weight
111
+ arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=1,dataloader_pin_memory=False,output_dir=tgt,overwrite_output_dir=True,save_total_limit=2,learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
112
+ trn=Trainer(args=arg,data_collator=DefaultDataCollator(),model=mdl,train_dataset=trainDS)
113
+ trn.train()
114
+ trn.save_model(tgt)
115
+ otk.save_pretrained(tgt)
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f1a1aedbdafb2390308d89af6ba632c559ee3c72a5ea95954fdccc2fddff61
3
+ size 1418925026
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,4079 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|fim_pre|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|fim_mid|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|fim_suf|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|im_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|im_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|tool_list_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|tool_list_end|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|tool_call_start|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|tool_call_end|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|tool_response_start|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|tool_response_end|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "16": {
118
+ "content": "<|reserved_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "17": {
126
+ "content": "<|reserved_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "18": {
134
+ "content": "<|reserved_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "19": {
142
+ "content": "<|reserved_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "20": {
150
+ "content": "<|reserved_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "21": {
158
+ "content": "<|reserved_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "22": {
166
+ "content": "<|reserved_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "23": {
174
+ "content": "<|reserved_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "24": {
182
+ "content": "<|reserved_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "25": {
190
+ "content": "<|reserved_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "26": {
198
+ "content": "<|reserved_16|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "27": {
206
+ "content": "<|reserved_17|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "28": {
214
+ "content": "<|reserved_18|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "29": {
222
+ "content": "<|reserved_19|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "30": {
230
+ "content": "<|reserved_20|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "31": {
238
+ "content": "<|reserved_21|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32": {
246
+ "content": "<|reserved_22|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "33": {
254
+ "content": "<|reserved_23|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "34": {
262
+ "content": "<|reserved_24|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "35": {
270
+ "content": "<|reserved_25|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "36": {
278
+ "content": "<|reserved_26|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "37": {
286
+ "content": "<|reserved_27|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "38": {
294
+ "content": "<|reserved_28|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "39": {
302
+ "content": "<|reserved_29|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "40": {
310
+ "content": "<|reserved_30|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "41": {
318
+ "content": "<|reserved_31|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "42": {
326
+ "content": "<|reserved_32|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "43": {
334
+ "content": "<|reserved_33|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "44": {
342
+ "content": "<|reserved_34|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "45": {
350
+ "content": "<|reserved_35|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "46": {
358
+ "content": "<|reserved_36|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "47": {
366
+ "content": "<|reserved_37|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "48": {
374
+ "content": "<|reserved_38|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "49": {
382
+ "content": "<|reserved_39|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "50": {
390
+ "content": "<|reserved_40|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "51": {
398
+ "content": "<|reserved_41|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "52": {
406
+ "content": "<|reserved_42|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "53": {
414
+ "content": "<|reserved_43|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "54": {
422
+ "content": "<|reserved_44|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "55": {
430
+ "content": "<|reserved_45|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "56": {
438
+ "content": "<|reserved_46|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "57": {
446
+ "content": "<|reserved_47|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "58": {
454
+ "content": "<|reserved_48|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "59": {
462
+ "content": "<|reserved_49|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "60": {
470
+ "content": "<|reserved_50|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "61": {
478
+ "content": "<|reserved_51|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "62": {
486
+ "content": "<|reserved_52|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "63": {
494
+ "content": "<|reserved_53|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "64": {
502
+ "content": "<|reserved_54|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "65": {
510
+ "content": "<|reserved_55|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "66": {
518
+ "content": "<|reserved_56|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "67": {
526
+ "content": "<|reserved_57|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "68": {
534
+ "content": "<|reserved_58|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "69": {
542
+ "content": "<|reserved_59|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "70": {
550
+ "content": "<|reserved_60|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "71": {
558
+ "content": "<|reserved_61|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "72": {
566
+ "content": "<|reserved_62|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "73": {
574
+ "content": "<|reserved_63|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "74": {
582
+ "content": "<|reserved_64|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "75": {
590
+ "content": "<|reserved_65|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "76": {
598
+ "content": "<|reserved_66|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "77": {
606
+ "content": "<|reserved_67|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "78": {
614
+ "content": "<|reserved_68|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "79": {
622
+ "content": "<|reserved_69|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "80": {
630
+ "content": "<|reserved_70|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "81": {
638
+ "content": "<|reserved_71|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "82": {
646
+ "content": "<|reserved_72|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "83": {
654
+ "content": "<|reserved_73|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "84": {
662
+ "content": "<|reserved_74|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "85": {
670
+ "content": "<|reserved_75|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "86": {
678
+ "content": "<|reserved_76|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "87": {
686
+ "content": "<|reserved_77|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "88": {
694
+ "content": "<|reserved_78|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "89": {
702
+ "content": "<|reserved_79|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "90": {
710
+ "content": "<|reserved_80|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "91": {
718
+ "content": "<|reserved_81|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "92": {
726
+ "content": "<|reserved_82|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "93": {
734
+ "content": "<|reserved_83|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "94": {
742
+ "content": "<|reserved_84|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "95": {
750
+ "content": "<|reserved_85|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "96": {
758
+ "content": "<|reserved_86|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "97": {
766
+ "content": "<|reserved_87|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "98": {
774
+ "content": "<|reserved_88|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "99": {
782
+ "content": "<|reserved_89|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "100": {
790
+ "content": "<|reserved_90|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "101": {
798
+ "content": "<|reserved_91|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "102": {
806
+ "content": "<|reserved_92|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "103": {
814
+ "content": "<|reserved_93|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "104": {
822
+ "content": "<|reserved_94|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "105": {
830
+ "content": "<|reserved_95|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "106": {
838
+ "content": "<|reserved_96|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "107": {
846
+ "content": "<|reserved_97|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "108": {
854
+ "content": "<|reserved_98|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "109": {
862
+ "content": "<|reserved_99|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "110": {
870
+ "content": "<|reserved_100|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "111": {
878
+ "content": "<|reserved_101|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "112": {
886
+ "content": "<|reserved_102|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "113": {
894
+ "content": "<|reserved_103|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "114": {
902
+ "content": "<|reserved_104|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "115": {
910
+ "content": "<|reserved_105|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "116": {
918
+ "content": "<|reserved_106|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "117": {
926
+ "content": "<|reserved_107|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "118": {
934
+ "content": "<|reserved_108|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "119": {
942
+ "content": "<|reserved_109|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "120": {
950
+ "content": "<|reserved_110|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "121": {
958
+ "content": "<|reserved_111|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "122": {
966
+ "content": "<|reserved_112|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "123": {
974
+ "content": "<|reserved_113|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "124": {
982
+ "content": "<|reserved_114|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "125": {
990
+ "content": "<|reserved_115|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "126": {
998
+ "content": "<|reserved_116|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "127": {
1006
+ "content": "<|reserved_117|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "128": {
1014
+ "content": "<|reserved_118|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "129": {
1022
+ "content": "<|reserved_119|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "130": {
1030
+ "content": "<|reserved_120|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "131": {
1038
+ "content": "<|reserved_121|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "132": {
1046
+ "content": "<|reserved_122|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "133": {
1054
+ "content": "<|reserved_123|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "134": {
1062
+ "content": "<|reserved_124|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "135": {
1070
+ "content": "<|reserved_125|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "136": {
1078
+ "content": "<|reserved_126|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "137": {
1086
+ "content": "<|reserved_127|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "138": {
1094
+ "content": "<|reserved_128|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "139": {
1102
+ "content": "<|reserved_129|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "140": {
1110
+ "content": "<|reserved_130|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "141": {
1118
+ "content": "<|reserved_131|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "142": {
1126
+ "content": "<|reserved_132|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "143": {
1134
+ "content": "<|reserved_133|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "144": {
1142
+ "content": "<|reserved_134|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "145": {
1150
+ "content": "<|reserved_135|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "146": {
1158
+ "content": "<|reserved_136|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "147": {
1166
+ "content": "<|reserved_137|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "148": {
1174
+ "content": "<|reserved_138|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "149": {
1182
+ "content": "<|reserved_139|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "150": {
1190
+ "content": "<|reserved_140|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151": {
1198
+ "content": "<|reserved_141|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "152": {
1206
+ "content": "<|reserved_142|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "153": {
1214
+ "content": "<|reserved_143|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "154": {
1222
+ "content": "<|reserved_144|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "155": {
1230
+ "content": "<|reserved_145|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "156": {
1238
+ "content": "<|reserved_146|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "157": {
1246
+ "content": "<|reserved_147|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "158": {
1254
+ "content": "<|reserved_148|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "159": {
1262
+ "content": "<|reserved_149|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "160": {
1270
+ "content": "<|reserved_150|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "161": {
1278
+ "content": "<|reserved_151|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "162": {
1286
+ "content": "<|reserved_152|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "163": {
1294
+ "content": "<|reserved_153|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "164": {
1302
+ "content": "<|reserved_154|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "165": {
1310
+ "content": "<|reserved_155|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "166": {
1318
+ "content": "<|reserved_156|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "167": {
1326
+ "content": "<|reserved_157|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "168": {
1334
+ "content": "<|reserved_158|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "169": {
1342
+ "content": "<|reserved_159|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "170": {
1350
+ "content": "<|reserved_160|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "171": {
1358
+ "content": "<|reserved_161|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "172": {
1366
+ "content": "<|reserved_162|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "173": {
1374
+ "content": "<|reserved_163|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "174": {
1382
+ "content": "<|reserved_164|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "175": {
1390
+ "content": "<|reserved_165|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "176": {
1398
+ "content": "<|reserved_166|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "177": {
1406
+ "content": "<|reserved_167|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "178": {
1414
+ "content": "<|reserved_168|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "179": {
1422
+ "content": "<|reserved_169|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "180": {
1430
+ "content": "<|reserved_170|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "181": {
1438
+ "content": "<|reserved_171|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "182": {
1446
+ "content": "<|reserved_172|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "183": {
1454
+ "content": "<|reserved_173|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "184": {
1462
+ "content": "<|reserved_174|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "185": {
1470
+ "content": "<|reserved_175|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "186": {
1478
+ "content": "<|reserved_176|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "187": {
1486
+ "content": "<|reserved_177|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "188": {
1494
+ "content": "<|reserved_178|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "189": {
1502
+ "content": "<|reserved_179|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "190": {
1510
+ "content": "<|reserved_180|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "191": {
1518
+ "content": "<|reserved_181|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "192": {
1526
+ "content": "<|reserved_182|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "193": {
1534
+ "content": "<|reserved_183|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "194": {
1542
+ "content": "<|reserved_184|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "195": {
1550
+ "content": "<|reserved_185|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "196": {
1558
+ "content": "<|reserved_186|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "197": {
1566
+ "content": "<|reserved_187|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "198": {
1574
+ "content": "<|reserved_188|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "199": {
1582
+ "content": "<|reserved_189|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "200": {
1590
+ "content": "<|reserved_190|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "201": {
1598
+ "content": "<|reserved_191|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "202": {
1606
+ "content": "<|reserved_192|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "203": {
1614
+ "content": "<|reserved_193|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "204": {
1622
+ "content": "<|reserved_194|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "205": {
1630
+ "content": "<|reserved_195|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "206": {
1638
+ "content": "<|reserved_196|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "207": {
1646
+ "content": "<|reserved_197|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "208": {
1654
+ "content": "<|reserved_198|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "209": {
1662
+ "content": "<|reserved_199|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "210": {
1670
+ "content": "<|reserved_200|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "211": {
1678
+ "content": "<|reserved_201|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "212": {
1686
+ "content": "<|reserved_202|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "213": {
1694
+ "content": "<|reserved_203|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "214": {
1702
+ "content": "<|reserved_204|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "215": {
1710
+ "content": "<|reserved_205|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "216": {
1718
+ "content": "<|reserved_206|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "217": {
1726
+ "content": "<|reserved_207|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "218": {
1734
+ "content": "<|reserved_208|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "219": {
1742
+ "content": "<|reserved_209|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "220": {
1750
+ "content": "<|reserved_210|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "221": {
1758
+ "content": "<|reserved_211|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "222": {
1766
+ "content": "<|reserved_212|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "223": {
1774
+ "content": "<|reserved_213|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "224": {
1782
+ "content": "<|reserved_214|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "225": {
1790
+ "content": "<|reserved_215|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "226": {
1798
+ "content": "<|reserved_216|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "227": {
1806
+ "content": "<|reserved_217|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "228": {
1814
+ "content": "<|reserved_218|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "229": {
1822
+ "content": "<|reserved_219|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "230": {
1830
+ "content": "<|reserved_220|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "231": {
1838
+ "content": "<|reserved_221|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "232": {
1846
+ "content": "<|reserved_222|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "233": {
1854
+ "content": "<|reserved_223|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "234": {
1862
+ "content": "<|reserved_224|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "235": {
1870
+ "content": "<|reserved_225|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "236": {
1878
+ "content": "<|reserved_226|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "237": {
1886
+ "content": "<|reserved_227|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "238": {
1894
+ "content": "<|reserved_228|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "239": {
1902
+ "content": "<|reserved_229|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "240": {
1910
+ "content": "<|reserved_230|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "241": {
1918
+ "content": "<|reserved_231|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "242": {
1926
+ "content": "<|reserved_232|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "243": {
1934
+ "content": "<|reserved_233|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "244": {
1942
+ "content": "<|reserved_234|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "245": {
1950
+ "content": "<|reserved_235|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "246": {
1958
+ "content": "<|reserved_236|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "247": {
1966
+ "content": "<|reserved_237|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "248": {
1974
+ "content": "<|reserved_238|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "249": {
1982
+ "content": "<|reserved_239|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "250": {
1990
+ "content": "<|reserved_240|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "251": {
1998
+ "content": "<|reserved_241|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "252": {
2006
+ "content": "<|reserved_242|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "253": {
2014
+ "content": "<|reserved_243|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "254": {
2022
+ "content": "<|reserved_244|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "255": {
2030
+ "content": "<|reserved_245|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "256": {
2038
+ "content": "<|reserved_246|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "257": {
2046
+ "content": "<|reserved_247|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "258": {
2054
+ "content": "<|reserved_248|>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "259": {
2062
+ "content": "<|reserved_249|>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "260": {
2070
+ "content": "<|reserved_250|>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ },
2077
+ "261": {
2078
+ "content": "<|reserved_251|>",
2079
+ "lstrip": false,
2080
+ "normalized": false,
2081
+ "rstrip": false,
2082
+ "single_word": false,
2083
+ "special": true
2084
+ },
2085
+ "262": {
2086
+ "content": "<|reserved_252|>",
2087
+ "lstrip": false,
2088
+ "normalized": false,
2089
+ "rstrip": false,
2090
+ "single_word": false,
2091
+ "special": true
2092
+ },
2093
+ "263": {
2094
+ "content": "<|reserved_253|>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": true
2100
+ },
2101
+ "264": {
2102
+ "content": "<|reserved_254|>",
2103
+ "lstrip": false,
2104
+ "normalized": false,
2105
+ "rstrip": false,
2106
+ "single_word": false,
2107
+ "special": true
2108
+ },
2109
+ "265": {
2110
+ "content": "<|reserved_255|>",
2111
+ "lstrip": false,
2112
+ "normalized": false,
2113
+ "rstrip": false,
2114
+ "single_word": false,
2115
+ "special": true
2116
+ },
2117
+ "266": {
2118
+ "content": "<|reserved_256|>",
2119
+ "lstrip": false,
2120
+ "normalized": false,
2121
+ "rstrip": false,
2122
+ "single_word": false,
2123
+ "special": true
2124
+ },
2125
+ "267": {
2126
+ "content": "<|reserved_257|>",
2127
+ "lstrip": false,
2128
+ "normalized": false,
2129
+ "rstrip": false,
2130
+ "single_word": false,
2131
+ "special": true
2132
+ },
2133
+ "268": {
2134
+ "content": "<|reserved_258|>",
2135
+ "lstrip": false,
2136
+ "normalized": false,
2137
+ "rstrip": false,
2138
+ "single_word": false,
2139
+ "special": true
2140
+ },
2141
+ "269": {
2142
+ "content": "<|reserved_259|>",
2143
+ "lstrip": false,
2144
+ "normalized": false,
2145
+ "rstrip": false,
2146
+ "single_word": false,
2147
+ "special": true
2148
+ },
2149
+ "270": {
2150
+ "content": "<|reserved_260|>",
2151
+ "lstrip": false,
2152
+ "normalized": false,
2153
+ "rstrip": false,
2154
+ "single_word": false,
2155
+ "special": true
2156
+ },
2157
+ "271": {
2158
+ "content": "<|reserved_261|>",
2159
+ "lstrip": false,
2160
+ "normalized": false,
2161
+ "rstrip": false,
2162
+ "single_word": false,
2163
+ "special": true
2164
+ },
2165
+ "272": {
2166
+ "content": "<|reserved_262|>",
2167
+ "lstrip": false,
2168
+ "normalized": false,
2169
+ "rstrip": false,
2170
+ "single_word": false,
2171
+ "special": true
2172
+ },
2173
+ "273": {
2174
+ "content": "<|reserved_263|>",
2175
+ "lstrip": false,
2176
+ "normalized": false,
2177
+ "rstrip": false,
2178
+ "single_word": false,
2179
+ "special": true
2180
+ },
2181
+ "274": {
2182
+ "content": "<|reserved_264|>",
2183
+ "lstrip": false,
2184
+ "normalized": false,
2185
+ "rstrip": false,
2186
+ "single_word": false,
2187
+ "special": true
2188
+ },
2189
+ "275": {
2190
+ "content": "<|reserved_265|>",
2191
+ "lstrip": false,
2192
+ "normalized": false,
2193
+ "rstrip": false,
2194
+ "single_word": false,
2195
+ "special": true
2196
+ },
2197
+ "276": {
2198
+ "content": "<|reserved_266|>",
2199
+ "lstrip": false,
2200
+ "normalized": false,
2201
+ "rstrip": false,
2202
+ "single_word": false,
2203
+ "special": true
2204
+ },
2205
+ "277": {
2206
+ "content": "<|reserved_267|>",
2207
+ "lstrip": false,
2208
+ "normalized": false,
2209
+ "rstrip": false,
2210
+ "single_word": false,
2211
+ "special": true
2212
+ },
2213
+ "278": {
2214
+ "content": "<|reserved_268|>",
2215
+ "lstrip": false,
2216
+ "normalized": false,
2217
+ "rstrip": false,
2218
+ "single_word": false,
2219
+ "special": true
2220
+ },
2221
+ "279": {
2222
+ "content": "<|reserved_269|>",
2223
+ "lstrip": false,
2224
+ "normalized": false,
2225
+ "rstrip": false,
2226
+ "single_word": false,
2227
+ "special": true
2228
+ },
2229
+ "280": {
2230
+ "content": "<|reserved_270|>",
2231
+ "lstrip": false,
2232
+ "normalized": false,
2233
+ "rstrip": false,
2234
+ "single_word": false,
2235
+ "special": true
2236
+ },
2237
+ "281": {
2238
+ "content": "<|reserved_271|>",
2239
+ "lstrip": false,
2240
+ "normalized": false,
2241
+ "rstrip": false,
2242
+ "single_word": false,
2243
+ "special": true
2244
+ },
2245
+ "282": {
2246
+ "content": "<|reserved_272|>",
2247
+ "lstrip": false,
2248
+ "normalized": false,
2249
+ "rstrip": false,
2250
+ "single_word": false,
2251
+ "special": true
2252
+ },
2253
+ "283": {
2254
+ "content": "<|reserved_273|>",
2255
+ "lstrip": false,
2256
+ "normalized": false,
2257
+ "rstrip": false,
2258
+ "single_word": false,
2259
+ "special": true
2260
+ },
2261
+ "284": {
2262
+ "content": "<|reserved_274|>",
2263
+ "lstrip": false,
2264
+ "normalized": false,
2265
+ "rstrip": false,
2266
+ "single_word": false,
2267
+ "special": true
2268
+ },
2269
+ "285": {
2270
+ "content": "<|reserved_275|>",
2271
+ "lstrip": false,
2272
+ "normalized": false,
2273
+ "rstrip": false,
2274
+ "single_word": false,
2275
+ "special": true
2276
+ },
2277
+ "286": {
2278
+ "content": "<|reserved_276|>",
2279
+ "lstrip": false,
2280
+ "normalized": false,
2281
+ "rstrip": false,
2282
+ "single_word": false,
2283
+ "special": true
2284
+ },
2285
+ "287": {
2286
+ "content": "<|reserved_277|>",
2287
+ "lstrip": false,
2288
+ "normalized": false,
2289
+ "rstrip": false,
2290
+ "single_word": false,
2291
+ "special": true
2292
+ },
2293
+ "288": {
2294
+ "content": "<|reserved_278|>",
2295
+ "lstrip": false,
2296
+ "normalized": false,
2297
+ "rstrip": false,
2298
+ "single_word": false,
2299
+ "special": true
2300
+ },
2301
+ "289": {
2302
+ "content": "<|reserved_279|>",
2303
+ "lstrip": false,
2304
+ "normalized": false,
2305
+ "rstrip": false,
2306
+ "single_word": false,
2307
+ "special": true
2308
+ },
2309
+ "290": {
2310
+ "content": "<|reserved_280|>",
2311
+ "lstrip": false,
2312
+ "normalized": false,
2313
+ "rstrip": false,
2314
+ "single_word": false,
2315
+ "special": true
2316
+ },
2317
+ "291": {
2318
+ "content": "<|reserved_281|>",
2319
+ "lstrip": false,
2320
+ "normalized": false,
2321
+ "rstrip": false,
2322
+ "single_word": false,
2323
+ "special": true
2324
+ },
2325
+ "292": {
2326
+ "content": "<|reserved_282|>",
2327
+ "lstrip": false,
2328
+ "normalized": false,
2329
+ "rstrip": false,
2330
+ "single_word": false,
2331
+ "special": true
2332
+ },
2333
+ "293": {
2334
+ "content": "<|reserved_283|>",
2335
+ "lstrip": false,
2336
+ "normalized": false,
2337
+ "rstrip": false,
2338
+ "single_word": false,
2339
+ "special": true
2340
+ },
2341
+ "294": {
2342
+ "content": "<|reserved_284|>",
2343
+ "lstrip": false,
2344
+ "normalized": false,
2345
+ "rstrip": false,
2346
+ "single_word": false,
2347
+ "special": true
2348
+ },
2349
+ "295": {
2350
+ "content": "<|reserved_285|>",
2351
+ "lstrip": false,
2352
+ "normalized": false,
2353
+ "rstrip": false,
2354
+ "single_word": false,
2355
+ "special": true
2356
+ },
2357
+ "296": {
2358
+ "content": "<|reserved_286|>",
2359
+ "lstrip": false,
2360
+ "normalized": false,
2361
+ "rstrip": false,
2362
+ "single_word": false,
2363
+ "special": true
2364
+ },
2365
+ "297": {
2366
+ "content": "<|reserved_287|>",
2367
+ "lstrip": false,
2368
+ "normalized": false,
2369
+ "rstrip": false,
2370
+ "single_word": false,
2371
+ "special": true
2372
+ },
2373
+ "298": {
2374
+ "content": "<|reserved_288|>",
2375
+ "lstrip": false,
2376
+ "normalized": false,
2377
+ "rstrip": false,
2378
+ "single_word": false,
2379
+ "special": true
2380
+ },
2381
+ "299": {
2382
+ "content": "<|reserved_289|>",
2383
+ "lstrip": false,
2384
+ "normalized": false,
2385
+ "rstrip": false,
2386
+ "single_word": false,
2387
+ "special": true
2388
+ },
2389
+ "300": {
2390
+ "content": "<|reserved_290|>",
2391
+ "lstrip": false,
2392
+ "normalized": false,
2393
+ "rstrip": false,
2394
+ "single_word": false,
2395
+ "special": true
2396
+ },
2397
+ "301": {
2398
+ "content": "<|reserved_291|>",
2399
+ "lstrip": false,
2400
+ "normalized": false,
2401
+ "rstrip": false,
2402
+ "single_word": false,
2403
+ "special": true
2404
+ },
2405
+ "302": {
2406
+ "content": "<|reserved_292|>",
2407
+ "lstrip": false,
2408
+ "normalized": false,
2409
+ "rstrip": false,
2410
+ "single_word": false,
2411
+ "special": true
2412
+ },
2413
+ "303": {
2414
+ "content": "<|reserved_293|>",
2415
+ "lstrip": false,
2416
+ "normalized": false,
2417
+ "rstrip": false,
2418
+ "single_word": false,
2419
+ "special": true
2420
+ },
2421
+ "304": {
2422
+ "content": "<|reserved_294|>",
2423
+ "lstrip": false,
2424
+ "normalized": false,
2425
+ "rstrip": false,
2426
+ "single_word": false,
2427
+ "special": true
2428
+ },
2429
+ "305": {
2430
+ "content": "<|reserved_295|>",
2431
+ "lstrip": false,
2432
+ "normalized": false,
2433
+ "rstrip": false,
2434
+ "single_word": false,
2435
+ "special": true
2436
+ },
2437
+ "306": {
2438
+ "content": "<|reserved_296|>",
2439
+ "lstrip": false,
2440
+ "normalized": false,
2441
+ "rstrip": false,
2442
+ "single_word": false,
2443
+ "special": true
2444
+ },
2445
+ "307": {
2446
+ "content": "<|reserved_297|>",
2447
+ "lstrip": false,
2448
+ "normalized": false,
2449
+ "rstrip": false,
2450
+ "single_word": false,
2451
+ "special": true
2452
+ },
2453
+ "308": {
2454
+ "content": "<|reserved_298|>",
2455
+ "lstrip": false,
2456
+ "normalized": false,
2457
+ "rstrip": false,
2458
+ "single_word": false,
2459
+ "special": true
2460
+ },
2461
+ "309": {
2462
+ "content": "<|reserved_299|>",
2463
+ "lstrip": false,
2464
+ "normalized": false,
2465
+ "rstrip": false,
2466
+ "single_word": false,
2467
+ "special": true
2468
+ },
2469
+ "310": {
2470
+ "content": "<|reserved_300|>",
2471
+ "lstrip": false,
2472
+ "normalized": false,
2473
+ "rstrip": false,
2474
+ "single_word": false,
2475
+ "special": true
2476
+ },
2477
+ "311": {
2478
+ "content": "<|reserved_301|>",
2479
+ "lstrip": false,
2480
+ "normalized": false,
2481
+ "rstrip": false,
2482
+ "single_word": false,
2483
+ "special": true
2484
+ },
2485
+ "312": {
2486
+ "content": "<|reserved_302|>",
2487
+ "lstrip": false,
2488
+ "normalized": false,
2489
+ "rstrip": false,
2490
+ "single_word": false,
2491
+ "special": true
2492
+ },
2493
+ "313": {
2494
+ "content": "<|reserved_303|>",
2495
+ "lstrip": false,
2496
+ "normalized": false,
2497
+ "rstrip": false,
2498
+ "single_word": false,
2499
+ "special": true
2500
+ },
2501
+ "314": {
2502
+ "content": "<|reserved_304|>",
2503
+ "lstrip": false,
2504
+ "normalized": false,
2505
+ "rstrip": false,
2506
+ "single_word": false,
2507
+ "special": true
2508
+ },
2509
+ "315": {
2510
+ "content": "<|reserved_305|>",
2511
+ "lstrip": false,
2512
+ "normalized": false,
2513
+ "rstrip": false,
2514
+ "single_word": false,
2515
+ "special": true
2516
+ },
2517
+ "316": {
2518
+ "content": "<|reserved_306|>",
2519
+ "lstrip": false,
2520
+ "normalized": false,
2521
+ "rstrip": false,
2522
+ "single_word": false,
2523
+ "special": true
2524
+ },
2525
+ "317": {
2526
+ "content": "<|reserved_307|>",
2527
+ "lstrip": false,
2528
+ "normalized": false,
2529
+ "rstrip": false,
2530
+ "single_word": false,
2531
+ "special": true
2532
+ },
2533
+ "318": {
2534
+ "content": "<|reserved_308|>",
2535
+ "lstrip": false,
2536
+ "normalized": false,
2537
+ "rstrip": false,
2538
+ "single_word": false,
2539
+ "special": true
2540
+ },
2541
+ "319": {
2542
+ "content": "<|reserved_309|>",
2543
+ "lstrip": false,
2544
+ "normalized": false,
2545
+ "rstrip": false,
2546
+ "single_word": false,
2547
+ "special": true
2548
+ },
2549
+ "320": {
2550
+ "content": "<|reserved_310|>",
2551
+ "lstrip": false,
2552
+ "normalized": false,
2553
+ "rstrip": false,
2554
+ "single_word": false,
2555
+ "special": true
2556
+ },
2557
+ "321": {
2558
+ "content": "<|reserved_311|>",
2559
+ "lstrip": false,
2560
+ "normalized": false,
2561
+ "rstrip": false,
2562
+ "single_word": false,
2563
+ "special": true
2564
+ },
2565
+ "322": {
2566
+ "content": "<|reserved_312|>",
2567
+ "lstrip": false,
2568
+ "normalized": false,
2569
+ "rstrip": false,
2570
+ "single_word": false,
2571
+ "special": true
2572
+ },
2573
+ "323": {
2574
+ "content": "<|reserved_313|>",
2575
+ "lstrip": false,
2576
+ "normalized": false,
2577
+ "rstrip": false,
2578
+ "single_word": false,
2579
+ "special": true
2580
+ },
2581
+ "324": {
2582
+ "content": "<|reserved_314|>",
2583
+ "lstrip": false,
2584
+ "normalized": false,
2585
+ "rstrip": false,
2586
+ "single_word": false,
2587
+ "special": true
2588
+ },
2589
+ "325": {
2590
+ "content": "<|reserved_315|>",
2591
+ "lstrip": false,
2592
+ "normalized": false,
2593
+ "rstrip": false,
2594
+ "single_word": false,
2595
+ "special": true
2596
+ },
2597
+ "326": {
2598
+ "content": "<|reserved_316|>",
2599
+ "lstrip": false,
2600
+ "normalized": false,
2601
+ "rstrip": false,
2602
+ "single_word": false,
2603
+ "special": true
2604
+ },
2605
+ "327": {
2606
+ "content": "<|reserved_317|>",
2607
+ "lstrip": false,
2608
+ "normalized": false,
2609
+ "rstrip": false,
2610
+ "single_word": false,
2611
+ "special": true
2612
+ },
2613
+ "328": {
2614
+ "content": "<|reserved_318|>",
2615
+ "lstrip": false,
2616
+ "normalized": false,
2617
+ "rstrip": false,
2618
+ "single_word": false,
2619
+ "special": true
2620
+ },
2621
+ "329": {
2622
+ "content": "<|reserved_319|>",
2623
+ "lstrip": false,
2624
+ "normalized": false,
2625
+ "rstrip": false,
2626
+ "single_word": false,
2627
+ "special": true
2628
+ },
2629
+ "330": {
2630
+ "content": "<|reserved_320|>",
2631
+ "lstrip": false,
2632
+ "normalized": false,
2633
+ "rstrip": false,
2634
+ "single_word": false,
2635
+ "special": true
2636
+ },
2637
+ "331": {
2638
+ "content": "<|reserved_321|>",
2639
+ "lstrip": false,
2640
+ "normalized": false,
2641
+ "rstrip": false,
2642
+ "single_word": false,
2643
+ "special": true
2644
+ },
2645
+ "332": {
2646
+ "content": "<|reserved_322|>",
2647
+ "lstrip": false,
2648
+ "normalized": false,
2649
+ "rstrip": false,
2650
+ "single_word": false,
2651
+ "special": true
2652
+ },
2653
+ "333": {
2654
+ "content": "<|reserved_323|>",
2655
+ "lstrip": false,
2656
+ "normalized": false,
2657
+ "rstrip": false,
2658
+ "single_word": false,
2659
+ "special": true
2660
+ },
2661
+ "334": {
2662
+ "content": "<|reserved_324|>",
2663
+ "lstrip": false,
2664
+ "normalized": false,
2665
+ "rstrip": false,
2666
+ "single_word": false,
2667
+ "special": true
2668
+ },
2669
+ "335": {
2670
+ "content": "<|reserved_325|>",
2671
+ "lstrip": false,
2672
+ "normalized": false,
2673
+ "rstrip": false,
2674
+ "single_word": false,
2675
+ "special": true
2676
+ },
2677
+ "336": {
2678
+ "content": "<|reserved_326|>",
2679
+ "lstrip": false,
2680
+ "normalized": false,
2681
+ "rstrip": false,
2682
+ "single_word": false,
2683
+ "special": true
2684
+ },
2685
+ "337": {
2686
+ "content": "<|reserved_327|>",
2687
+ "lstrip": false,
2688
+ "normalized": false,
2689
+ "rstrip": false,
2690
+ "single_word": false,
2691
+ "special": true
2692
+ },
2693
+ "338": {
2694
+ "content": "<|reserved_328|>",
2695
+ "lstrip": false,
2696
+ "normalized": false,
2697
+ "rstrip": false,
2698
+ "single_word": false,
2699
+ "special": true
2700
+ },
2701
+ "339": {
2702
+ "content": "<|reserved_329|>",
2703
+ "lstrip": false,
2704
+ "normalized": false,
2705
+ "rstrip": false,
2706
+ "single_word": false,
2707
+ "special": true
2708
+ },
2709
+ "340": {
2710
+ "content": "<|reserved_330|>",
2711
+ "lstrip": false,
2712
+ "normalized": false,
2713
+ "rstrip": false,
2714
+ "single_word": false,
2715
+ "special": true
2716
+ },
2717
+ "341": {
2718
+ "content": "<|reserved_331|>",
2719
+ "lstrip": false,
2720
+ "normalized": false,
2721
+ "rstrip": false,
2722
+ "single_word": false,
2723
+ "special": true
2724
+ },
2725
+ "342": {
2726
+ "content": "<|reserved_332|>",
2727
+ "lstrip": false,
2728
+ "normalized": false,
2729
+ "rstrip": false,
2730
+ "single_word": false,
2731
+ "special": true
2732
+ },
2733
+ "343": {
2734
+ "content": "<|reserved_333|>",
2735
+ "lstrip": false,
2736
+ "normalized": false,
2737
+ "rstrip": false,
2738
+ "single_word": false,
2739
+ "special": true
2740
+ },
2741
+ "344": {
2742
+ "content": "<|reserved_334|>",
2743
+ "lstrip": false,
2744
+ "normalized": false,
2745
+ "rstrip": false,
2746
+ "single_word": false,
2747
+ "special": true
2748
+ },
2749
+ "345": {
2750
+ "content": "<|reserved_335|>",
2751
+ "lstrip": false,
2752
+ "normalized": false,
2753
+ "rstrip": false,
2754
+ "single_word": false,
2755
+ "special": true
2756
+ },
2757
+ "346": {
2758
+ "content": "<|reserved_336|>",
2759
+ "lstrip": false,
2760
+ "normalized": false,
2761
+ "rstrip": false,
2762
+ "single_word": false,
2763
+ "special": true
2764
+ },
2765
+ "347": {
2766
+ "content": "<|reserved_337|>",
2767
+ "lstrip": false,
2768
+ "normalized": false,
2769
+ "rstrip": false,
2770
+ "single_word": false,
2771
+ "special": true
2772
+ },
2773
+ "348": {
2774
+ "content": "<|reserved_338|>",
2775
+ "lstrip": false,
2776
+ "normalized": false,
2777
+ "rstrip": false,
2778
+ "single_word": false,
2779
+ "special": true
2780
+ },
2781
+ "349": {
2782
+ "content": "<|reserved_339|>",
2783
+ "lstrip": false,
2784
+ "normalized": false,
2785
+ "rstrip": false,
2786
+ "single_word": false,
2787
+ "special": true
2788
+ },
2789
+ "350": {
2790
+ "content": "<|reserved_340|>",
2791
+ "lstrip": false,
2792
+ "normalized": false,
2793
+ "rstrip": false,
2794
+ "single_word": false,
2795
+ "special": true
2796
+ },
2797
+ "351": {
2798
+ "content": "<|reserved_341|>",
2799
+ "lstrip": false,
2800
+ "normalized": false,
2801
+ "rstrip": false,
2802
+ "single_word": false,
2803
+ "special": true
2804
+ },
2805
+ "352": {
2806
+ "content": "<|reserved_342|>",
2807
+ "lstrip": false,
2808
+ "normalized": false,
2809
+ "rstrip": false,
2810
+ "single_word": false,
2811
+ "special": true
2812
+ },
2813
+ "353": {
2814
+ "content": "<|reserved_343|>",
2815
+ "lstrip": false,
2816
+ "normalized": false,
2817
+ "rstrip": false,
2818
+ "single_word": false,
2819
+ "special": true
2820
+ },
2821
+ "354": {
2822
+ "content": "<|reserved_344|>",
2823
+ "lstrip": false,
2824
+ "normalized": false,
2825
+ "rstrip": false,
2826
+ "single_word": false,
2827
+ "special": true
2828
+ },
2829
+ "355": {
2830
+ "content": "<|reserved_345|>",
2831
+ "lstrip": false,
2832
+ "normalized": false,
2833
+ "rstrip": false,
2834
+ "single_word": false,
2835
+ "special": true
2836
+ },
2837
+ "356": {
2838
+ "content": "<|reserved_346|>",
2839
+ "lstrip": false,
2840
+ "normalized": false,
2841
+ "rstrip": false,
2842
+ "single_word": false,
2843
+ "special": true
2844
+ },
2845
+ "357": {
2846
+ "content": "<|reserved_347|>",
2847
+ "lstrip": false,
2848
+ "normalized": false,
2849
+ "rstrip": false,
2850
+ "single_word": false,
2851
+ "special": true
2852
+ },
2853
+ "358": {
2854
+ "content": "<|reserved_348|>",
2855
+ "lstrip": false,
2856
+ "normalized": false,
2857
+ "rstrip": false,
2858
+ "single_word": false,
2859
+ "special": true
2860
+ },
2861
+ "359": {
2862
+ "content": "<|reserved_349|>",
2863
+ "lstrip": false,
2864
+ "normalized": false,
2865
+ "rstrip": false,
2866
+ "single_word": false,
2867
+ "special": true
2868
+ },
2869
+ "360": {
2870
+ "content": "<|reserved_350|>",
2871
+ "lstrip": false,
2872
+ "normalized": false,
2873
+ "rstrip": false,
2874
+ "single_word": false,
2875
+ "special": true
2876
+ },
2877
+ "361": {
2878
+ "content": "<|reserved_351|>",
2879
+ "lstrip": false,
2880
+ "normalized": false,
2881
+ "rstrip": false,
2882
+ "single_word": false,
2883
+ "special": true
2884
+ },
2885
+ "362": {
2886
+ "content": "<|reserved_352|>",
2887
+ "lstrip": false,
2888
+ "normalized": false,
2889
+ "rstrip": false,
2890
+ "single_word": false,
2891
+ "special": true
2892
+ },
2893
+ "363": {
2894
+ "content": "<|reserved_353|>",
2895
+ "lstrip": false,
2896
+ "normalized": false,
2897
+ "rstrip": false,
2898
+ "single_word": false,
2899
+ "special": true
2900
+ },
2901
+ "364": {
2902
+ "content": "<|reserved_354|>",
2903
+ "lstrip": false,
2904
+ "normalized": false,
2905
+ "rstrip": false,
2906
+ "single_word": false,
2907
+ "special": true
2908
+ },
2909
+ "365": {
2910
+ "content": "<|reserved_355|>",
2911
+ "lstrip": false,
2912
+ "normalized": false,
2913
+ "rstrip": false,
2914
+ "single_word": false,
2915
+ "special": true
2916
+ },
2917
+ "366": {
2918
+ "content": "<|reserved_356|>",
2919
+ "lstrip": false,
2920
+ "normalized": false,
2921
+ "rstrip": false,
2922
+ "single_word": false,
2923
+ "special": true
2924
+ },
2925
+ "367": {
2926
+ "content": "<|reserved_357|>",
2927
+ "lstrip": false,
2928
+ "normalized": false,
2929
+ "rstrip": false,
2930
+ "single_word": false,
2931
+ "special": true
2932
+ },
2933
+ "368": {
2934
+ "content": "<|reserved_358|>",
2935
+ "lstrip": false,
2936
+ "normalized": false,
2937
+ "rstrip": false,
2938
+ "single_word": false,
2939
+ "special": true
2940
+ },
2941
+ "369": {
2942
+ "content": "<|reserved_359|>",
2943
+ "lstrip": false,
2944
+ "normalized": false,
2945
+ "rstrip": false,
2946
+ "single_word": false,
2947
+ "special": true
2948
+ },
2949
+ "370": {
2950
+ "content": "<|reserved_360|>",
2951
+ "lstrip": false,
2952
+ "normalized": false,
2953
+ "rstrip": false,
2954
+ "single_word": false,
2955
+ "special": true
2956
+ },
2957
+ "371": {
2958
+ "content": "<|reserved_361|>",
2959
+ "lstrip": false,
2960
+ "normalized": false,
2961
+ "rstrip": false,
2962
+ "single_word": false,
2963
+ "special": true
2964
+ },
2965
+ "372": {
2966
+ "content": "<|reserved_362|>",
2967
+ "lstrip": false,
2968
+ "normalized": false,
2969
+ "rstrip": false,
2970
+ "single_word": false,
2971
+ "special": true
2972
+ },
2973
+ "373": {
2974
+ "content": "<|reserved_363|>",
2975
+ "lstrip": false,
2976
+ "normalized": false,
2977
+ "rstrip": false,
2978
+ "single_word": false,
2979
+ "special": true
2980
+ },
2981
+ "374": {
2982
+ "content": "<|reserved_364|>",
2983
+ "lstrip": false,
2984
+ "normalized": false,
2985
+ "rstrip": false,
2986
+ "single_word": false,
2987
+ "special": true
2988
+ },
2989
+ "375": {
2990
+ "content": "<|reserved_365|>",
2991
+ "lstrip": false,
2992
+ "normalized": false,
2993
+ "rstrip": false,
2994
+ "single_word": false,
2995
+ "special": true
2996
+ },
2997
+ "376": {
2998
+ "content": "<|reserved_366|>",
2999
+ "lstrip": false,
3000
+ "normalized": false,
3001
+ "rstrip": false,
3002
+ "single_word": false,
3003
+ "special": true
3004
+ },
3005
+ "377": {
3006
+ "content": "<|reserved_367|>",
3007
+ "lstrip": false,
3008
+ "normalized": false,
3009
+ "rstrip": false,
3010
+ "single_word": false,
3011
+ "special": true
3012
+ },
3013
+ "378": {
3014
+ "content": "<|reserved_368|>",
3015
+ "lstrip": false,
3016
+ "normalized": false,
3017
+ "rstrip": false,
3018
+ "single_word": false,
3019
+ "special": true
3020
+ },
3021
+ "379": {
3022
+ "content": "<|reserved_369|>",
3023
+ "lstrip": false,
3024
+ "normalized": false,
3025
+ "rstrip": false,
3026
+ "single_word": false,
3027
+ "special": true
3028
+ },
3029
+ "380": {
3030
+ "content": "<|reserved_370|>",
3031
+ "lstrip": false,
3032
+ "normalized": false,
3033
+ "rstrip": false,
3034
+ "single_word": false,
3035
+ "special": true
3036
+ },
3037
+ "381": {
3038
+ "content": "<|reserved_371|>",
3039
+ "lstrip": false,
3040
+ "normalized": false,
3041
+ "rstrip": false,
3042
+ "single_word": false,
3043
+ "special": true
3044
+ },
3045
+ "382": {
3046
+ "content": "<|reserved_372|>",
3047
+ "lstrip": false,
3048
+ "normalized": false,
3049
+ "rstrip": false,
3050
+ "single_word": false,
3051
+ "special": true
3052
+ },
3053
+ "383": {
3054
+ "content": "<|reserved_373|>",
3055
+ "lstrip": false,
3056
+ "normalized": false,
3057
+ "rstrip": false,
3058
+ "single_word": false,
3059
+ "special": true
3060
+ },
3061
+ "384": {
3062
+ "content": "<|reserved_374|>",
3063
+ "lstrip": false,
3064
+ "normalized": false,
3065
+ "rstrip": false,
3066
+ "single_word": false,
3067
+ "special": true
3068
+ },
3069
+ "385": {
3070
+ "content": "<|reserved_375|>",
3071
+ "lstrip": false,
3072
+ "normalized": false,
3073
+ "rstrip": false,
3074
+ "single_word": false,
3075
+ "special": true
3076
+ },
3077
+ "386": {
3078
+ "content": "<|reserved_376|>",
3079
+ "lstrip": false,
3080
+ "normalized": false,
3081
+ "rstrip": false,
3082
+ "single_word": false,
3083
+ "special": true
3084
+ },
3085
+ "387": {
3086
+ "content": "<|reserved_377|>",
3087
+ "lstrip": false,
3088
+ "normalized": false,
3089
+ "rstrip": false,
3090
+ "single_word": false,
3091
+ "special": true
3092
+ },
3093
+ "388": {
3094
+ "content": "<|reserved_378|>",
3095
+ "lstrip": false,
3096
+ "normalized": false,
3097
+ "rstrip": false,
3098
+ "single_word": false,
3099
+ "special": true
3100
+ },
3101
+ "389": {
3102
+ "content": "<|reserved_379|>",
3103
+ "lstrip": false,
3104
+ "normalized": false,
3105
+ "rstrip": false,
3106
+ "single_word": false,
3107
+ "special": true
3108
+ },
3109
+ "390": {
3110
+ "content": "<|reserved_380|>",
3111
+ "lstrip": false,
3112
+ "normalized": false,
3113
+ "rstrip": false,
3114
+ "single_word": false,
3115
+ "special": true
3116
+ },
3117
+ "391": {
3118
+ "content": "<|reserved_381|>",
3119
+ "lstrip": false,
3120
+ "normalized": false,
3121
+ "rstrip": false,
3122
+ "single_word": false,
3123
+ "special": true
3124
+ },
3125
+ "392": {
3126
+ "content": "<|reserved_382|>",
3127
+ "lstrip": false,
3128
+ "normalized": false,
3129
+ "rstrip": false,
3130
+ "single_word": false,
3131
+ "special": true
3132
+ },
3133
+ "393": {
3134
+ "content": "<|reserved_383|>",
3135
+ "lstrip": false,
3136
+ "normalized": false,
3137
+ "rstrip": false,
3138
+ "single_word": false,
3139
+ "special": true
3140
+ },
3141
+ "394": {
3142
+ "content": "<|reserved_384|>",
3143
+ "lstrip": false,
3144
+ "normalized": false,
3145
+ "rstrip": false,
3146
+ "single_word": false,
3147
+ "special": true
3148
+ },
3149
+ "395": {
3150
+ "content": "<|reserved_385|>",
3151
+ "lstrip": false,
3152
+ "normalized": false,
3153
+ "rstrip": false,
3154
+ "single_word": false,
3155
+ "special": true
3156
+ },
3157
+ "396": {
3158
+ "content": "<|reserved_386|>",
3159
+ "lstrip": false,
3160
+ "normalized": false,
3161
+ "rstrip": false,
3162
+ "single_word": false,
3163
+ "special": true
3164
+ },
3165
+ "397": {
3166
+ "content": "<|reserved_387|>",
3167
+ "lstrip": false,
3168
+ "normalized": false,
3169
+ "rstrip": false,
3170
+ "single_word": false,
3171
+ "special": true
3172
+ },
3173
+ "398": {
3174
+ "content": "<|reserved_388|>",
3175
+ "lstrip": false,
3176
+ "normalized": false,
3177
+ "rstrip": false,
3178
+ "single_word": false,
3179
+ "special": true
3180
+ },
3181
+ "399": {
3182
+ "content": "<|reserved_389|>",
3183
+ "lstrip": false,
3184
+ "normalized": false,
3185
+ "rstrip": false,
3186
+ "single_word": false,
3187
+ "special": true
3188
+ },
3189
+ "400": {
3190
+ "content": "<|reserved_390|>",
3191
+ "lstrip": false,
3192
+ "normalized": false,
3193
+ "rstrip": false,
3194
+ "single_word": false,
3195
+ "special": true
3196
+ },
3197
+ "401": {
3198
+ "content": "<|reserved_391|>",
3199
+ "lstrip": false,
3200
+ "normalized": false,
3201
+ "rstrip": false,
3202
+ "single_word": false,
3203
+ "special": true
3204
+ },
3205
+ "402": {
3206
+ "content": "<|reserved_392|>",
3207
+ "lstrip": false,
3208
+ "normalized": false,
3209
+ "rstrip": false,
3210
+ "single_word": false,
3211
+ "special": true
3212
+ },
3213
+ "403": {
3214
+ "content": "<|reserved_393|>",
3215
+ "lstrip": false,
3216
+ "normalized": false,
3217
+ "rstrip": false,
3218
+ "single_word": false,
3219
+ "special": true
3220
+ },
3221
+ "404": {
3222
+ "content": "<|reserved_394|>",
3223
+ "lstrip": false,
3224
+ "normalized": false,
3225
+ "rstrip": false,
3226
+ "single_word": false,
3227
+ "special": true
3228
+ },
3229
+ "405": {
3230
+ "content": "<|reserved_395|>",
3231
+ "lstrip": false,
3232
+ "normalized": false,
3233
+ "rstrip": false,
3234
+ "single_word": false,
3235
+ "special": true
3236
+ },
3237
+ "406": {
3238
+ "content": "<|reserved_396|>",
3239
+ "lstrip": false,
3240
+ "normalized": false,
3241
+ "rstrip": false,
3242
+ "single_word": false,
3243
+ "special": true
3244
+ },
3245
+ "407": {
3246
+ "content": "<|reserved_397|>",
3247
+ "lstrip": false,
3248
+ "normalized": false,
3249
+ "rstrip": false,
3250
+ "single_word": false,
3251
+ "special": true
3252
+ },
3253
+ "408": {
3254
+ "content": "<|reserved_398|>",
3255
+ "lstrip": false,
3256
+ "normalized": false,
3257
+ "rstrip": false,
3258
+ "single_word": false,
3259
+ "special": true
3260
+ },
3261
+ "409": {
3262
+ "content": "<|reserved_399|>",
3263
+ "lstrip": false,
3264
+ "normalized": false,
3265
+ "rstrip": false,
3266
+ "single_word": false,
3267
+ "special": true
3268
+ },
3269
+ "410": {
3270
+ "content": "<|reserved_400|>",
3271
+ "lstrip": false,
3272
+ "normalized": false,
3273
+ "rstrip": false,
3274
+ "single_word": false,
3275
+ "special": true
3276
+ },
3277
+ "411": {
3278
+ "content": "<|reserved_401|>",
3279
+ "lstrip": false,
3280
+ "normalized": false,
3281
+ "rstrip": false,
3282
+ "single_word": false,
3283
+ "special": true
3284
+ },
3285
+ "412": {
3286
+ "content": "<|reserved_402|>",
3287
+ "lstrip": false,
3288
+ "normalized": false,
3289
+ "rstrip": false,
3290
+ "single_word": false,
3291
+ "special": true
3292
+ },
3293
+ "413": {
3294
+ "content": "<|reserved_403|>",
3295
+ "lstrip": false,
3296
+ "normalized": false,
3297
+ "rstrip": false,
3298
+ "single_word": false,
3299
+ "special": true
3300
+ },
3301
+ "414": {
3302
+ "content": "<|reserved_404|>",
3303
+ "lstrip": false,
3304
+ "normalized": false,
3305
+ "rstrip": false,
3306
+ "single_word": false,
3307
+ "special": true
3308
+ },
3309
+ "415": {
3310
+ "content": "<|reserved_405|>",
3311
+ "lstrip": false,
3312
+ "normalized": false,
3313
+ "rstrip": false,
3314
+ "single_word": false,
3315
+ "special": true
3316
+ },
3317
+ "416": {
3318
+ "content": "<|reserved_406|>",
3319
+ "lstrip": false,
3320
+ "normalized": false,
3321
+ "rstrip": false,
3322
+ "single_word": false,
3323
+ "special": true
3324
+ },
3325
+ "417": {
3326
+ "content": "<|reserved_407|>",
3327
+ "lstrip": false,
3328
+ "normalized": false,
3329
+ "rstrip": false,
3330
+ "single_word": false,
3331
+ "special": true
3332
+ },
3333
+ "418": {
3334
+ "content": "<|reserved_408|>",
3335
+ "lstrip": false,
3336
+ "normalized": false,
3337
+ "rstrip": false,
3338
+ "single_word": false,
3339
+ "special": true
3340
+ },
3341
+ "419": {
3342
+ "content": "<|reserved_409|>",
3343
+ "lstrip": false,
3344
+ "normalized": false,
3345
+ "rstrip": false,
3346
+ "single_word": false,
3347
+ "special": true
3348
+ },
3349
+ "420": {
3350
+ "content": "<|reserved_410|>",
3351
+ "lstrip": false,
3352
+ "normalized": false,
3353
+ "rstrip": false,
3354
+ "single_word": false,
3355
+ "special": true
3356
+ },
3357
+ "421": {
3358
+ "content": "<|reserved_411|>",
3359
+ "lstrip": false,
3360
+ "normalized": false,
3361
+ "rstrip": false,
3362
+ "single_word": false,
3363
+ "special": true
3364
+ },
3365
+ "422": {
3366
+ "content": "<|reserved_412|>",
3367
+ "lstrip": false,
3368
+ "normalized": false,
3369
+ "rstrip": false,
3370
+ "single_word": false,
3371
+ "special": true
3372
+ },
3373
+ "423": {
3374
+ "content": "<|reserved_413|>",
3375
+ "lstrip": false,
3376
+ "normalized": false,
3377
+ "rstrip": false,
3378
+ "single_word": false,
3379
+ "special": true
3380
+ },
3381
+ "424": {
3382
+ "content": "<|reserved_414|>",
3383
+ "lstrip": false,
3384
+ "normalized": false,
3385
+ "rstrip": false,
3386
+ "single_word": false,
3387
+ "special": true
3388
+ },
3389
+ "425": {
3390
+ "content": "<|reserved_415|>",
3391
+ "lstrip": false,
3392
+ "normalized": false,
3393
+ "rstrip": false,
3394
+ "single_word": false,
3395
+ "special": true
3396
+ },
3397
+ "426": {
3398
+ "content": "<|reserved_416|>",
3399
+ "lstrip": false,
3400
+ "normalized": false,
3401
+ "rstrip": false,
3402
+ "single_word": false,
3403
+ "special": true
3404
+ },
3405
+ "427": {
3406
+ "content": "<|reserved_417|>",
3407
+ "lstrip": false,
3408
+ "normalized": false,
3409
+ "rstrip": false,
3410
+ "single_word": false,
3411
+ "special": true
3412
+ },
3413
+ "428": {
3414
+ "content": "<|reserved_418|>",
3415
+ "lstrip": false,
3416
+ "normalized": false,
3417
+ "rstrip": false,
3418
+ "single_word": false,
3419
+ "special": true
3420
+ },
3421
+ "429": {
3422
+ "content": "<|reserved_419|>",
3423
+ "lstrip": false,
3424
+ "normalized": false,
3425
+ "rstrip": false,
3426
+ "single_word": false,
3427
+ "special": true
3428
+ },
3429
+ "430": {
3430
+ "content": "<|reserved_420|>",
3431
+ "lstrip": false,
3432
+ "normalized": false,
3433
+ "rstrip": false,
3434
+ "single_word": false,
3435
+ "special": true
3436
+ },
3437
+ "431": {
3438
+ "content": "<|reserved_421|>",
3439
+ "lstrip": false,
3440
+ "normalized": false,
3441
+ "rstrip": false,
3442
+ "single_word": false,
3443
+ "special": true
3444
+ },
3445
+ "432": {
3446
+ "content": "<|reserved_422|>",
3447
+ "lstrip": false,
3448
+ "normalized": false,
3449
+ "rstrip": false,
3450
+ "single_word": false,
3451
+ "special": true
3452
+ },
3453
+ "433": {
3454
+ "content": "<|reserved_423|>",
3455
+ "lstrip": false,
3456
+ "normalized": false,
3457
+ "rstrip": false,
3458
+ "single_word": false,
3459
+ "special": true
3460
+ },
3461
+ "434": {
3462
+ "content": "<|reserved_424|>",
3463
+ "lstrip": false,
3464
+ "normalized": false,
3465
+ "rstrip": false,
3466
+ "single_word": false,
3467
+ "special": true
3468
+ },
3469
+ "435": {
3470
+ "content": "<|reserved_425|>",
3471
+ "lstrip": false,
3472
+ "normalized": false,
3473
+ "rstrip": false,
3474
+ "single_word": false,
3475
+ "special": true
3476
+ },
3477
+ "436": {
3478
+ "content": "<|reserved_426|>",
3479
+ "lstrip": false,
3480
+ "normalized": false,
3481
+ "rstrip": false,
3482
+ "single_word": false,
3483
+ "special": true
3484
+ },
3485
+ "437": {
3486
+ "content": "<|reserved_427|>",
3487
+ "lstrip": false,
3488
+ "normalized": false,
3489
+ "rstrip": false,
3490
+ "single_word": false,
3491
+ "special": true
3492
+ },
3493
+ "438": {
3494
+ "content": "<|reserved_428|>",
3495
+ "lstrip": false,
3496
+ "normalized": false,
3497
+ "rstrip": false,
3498
+ "single_word": false,
3499
+ "special": true
3500
+ },
3501
+ "439": {
3502
+ "content": "<|reserved_429|>",
3503
+ "lstrip": false,
3504
+ "normalized": false,
3505
+ "rstrip": false,
3506
+ "single_word": false,
3507
+ "special": true
3508
+ },
3509
+ "440": {
3510
+ "content": "<|reserved_430|>",
3511
+ "lstrip": false,
3512
+ "normalized": false,
3513
+ "rstrip": false,
3514
+ "single_word": false,
3515
+ "special": true
3516
+ },
3517
+ "441": {
3518
+ "content": "<|reserved_431|>",
3519
+ "lstrip": false,
3520
+ "normalized": false,
3521
+ "rstrip": false,
3522
+ "single_word": false,
3523
+ "special": true
3524
+ },
3525
+ "442": {
3526
+ "content": "<|reserved_432|>",
3527
+ "lstrip": false,
3528
+ "normalized": false,
3529
+ "rstrip": false,
3530
+ "single_word": false,
3531
+ "special": true
3532
+ },
3533
+ "443": {
3534
+ "content": "<|reserved_433|>",
3535
+ "lstrip": false,
3536
+ "normalized": false,
3537
+ "rstrip": false,
3538
+ "single_word": false,
3539
+ "special": true
3540
+ },
3541
+ "444": {
3542
+ "content": "<|reserved_434|>",
3543
+ "lstrip": false,
3544
+ "normalized": false,
3545
+ "rstrip": false,
3546
+ "single_word": false,
3547
+ "special": true
3548
+ },
3549
+ "445": {
3550
+ "content": "<|reserved_435|>",
3551
+ "lstrip": false,
3552
+ "normalized": false,
3553
+ "rstrip": false,
3554
+ "single_word": false,
3555
+ "special": true
3556
+ },
3557
+ "446": {
3558
+ "content": "<|reserved_436|>",
3559
+ "lstrip": false,
3560
+ "normalized": false,
3561
+ "rstrip": false,
3562
+ "single_word": false,
3563
+ "special": true
3564
+ },
3565
+ "447": {
3566
+ "content": "<|reserved_437|>",
3567
+ "lstrip": false,
3568
+ "normalized": false,
3569
+ "rstrip": false,
3570
+ "single_word": false,
3571
+ "special": true
3572
+ },
3573
+ "448": {
3574
+ "content": "<|reserved_438|>",
3575
+ "lstrip": false,
3576
+ "normalized": false,
3577
+ "rstrip": false,
3578
+ "single_word": false,
3579
+ "special": true
3580
+ },
3581
+ "449": {
3582
+ "content": "<|reserved_439|>",
3583
+ "lstrip": false,
3584
+ "normalized": false,
3585
+ "rstrip": false,
3586
+ "single_word": false,
3587
+ "special": true
3588
+ },
3589
+ "450": {
3590
+ "content": "<|reserved_440|>",
3591
+ "lstrip": false,
3592
+ "normalized": false,
3593
+ "rstrip": false,
3594
+ "single_word": false,
3595
+ "special": true
3596
+ },
3597
+ "451": {
3598
+ "content": "<|reserved_441|>",
3599
+ "lstrip": false,
3600
+ "normalized": false,
3601
+ "rstrip": false,
3602
+ "single_word": false,
3603
+ "special": true
3604
+ },
3605
+ "452": {
3606
+ "content": "<|reserved_442|>",
3607
+ "lstrip": false,
3608
+ "normalized": false,
3609
+ "rstrip": false,
3610
+ "single_word": false,
3611
+ "special": true
3612
+ },
3613
+ "453": {
3614
+ "content": "<|reserved_443|>",
3615
+ "lstrip": false,
3616
+ "normalized": false,
3617
+ "rstrip": false,
3618
+ "single_word": false,
3619
+ "special": true
3620
+ },
3621
+ "454": {
3622
+ "content": "<|reserved_444|>",
3623
+ "lstrip": false,
3624
+ "normalized": false,
3625
+ "rstrip": false,
3626
+ "single_word": false,
3627
+ "special": true
3628
+ },
3629
+ "455": {
3630
+ "content": "<|reserved_445|>",
3631
+ "lstrip": false,
3632
+ "normalized": false,
3633
+ "rstrip": false,
3634
+ "single_word": false,
3635
+ "special": true
3636
+ },
3637
+ "456": {
3638
+ "content": "<|reserved_446|>",
3639
+ "lstrip": false,
3640
+ "normalized": false,
3641
+ "rstrip": false,
3642
+ "single_word": false,
3643
+ "special": true
3644
+ },
3645
+ "457": {
3646
+ "content": "<|reserved_447|>",
3647
+ "lstrip": false,
3648
+ "normalized": false,
3649
+ "rstrip": false,
3650
+ "single_word": false,
3651
+ "special": true
3652
+ },
3653
+ "458": {
3654
+ "content": "<|reserved_448|>",
3655
+ "lstrip": false,
3656
+ "normalized": false,
3657
+ "rstrip": false,
3658
+ "single_word": false,
3659
+ "special": true
3660
+ },
3661
+ "459": {
3662
+ "content": "<|reserved_449|>",
3663
+ "lstrip": false,
3664
+ "normalized": false,
3665
+ "rstrip": false,
3666
+ "single_word": false,
3667
+ "special": true
3668
+ },
3669
+ "460": {
3670
+ "content": "<|reserved_450|>",
3671
+ "lstrip": false,
3672
+ "normalized": false,
3673
+ "rstrip": false,
3674
+ "single_word": false,
3675
+ "special": true
3676
+ },
3677
+ "461": {
3678
+ "content": "<|reserved_451|>",
3679
+ "lstrip": false,
3680
+ "normalized": false,
3681
+ "rstrip": false,
3682
+ "single_word": false,
3683
+ "special": true
3684
+ },
3685
+ "462": {
3686
+ "content": "<|reserved_452|>",
3687
+ "lstrip": false,
3688
+ "normalized": false,
3689
+ "rstrip": false,
3690
+ "single_word": false,
3691
+ "special": true
3692
+ },
3693
+ "463": {
3694
+ "content": "<|reserved_453|>",
3695
+ "lstrip": false,
3696
+ "normalized": false,
3697
+ "rstrip": false,
3698
+ "single_word": false,
3699
+ "special": true
3700
+ },
3701
+ "464": {
3702
+ "content": "<|reserved_454|>",
3703
+ "lstrip": false,
3704
+ "normalized": false,
3705
+ "rstrip": false,
3706
+ "single_word": false,
3707
+ "special": true
3708
+ },
3709
+ "465": {
3710
+ "content": "<|reserved_455|>",
3711
+ "lstrip": false,
3712
+ "normalized": false,
3713
+ "rstrip": false,
3714
+ "single_word": false,
3715
+ "special": true
3716
+ },
3717
+ "466": {
3718
+ "content": "<|reserved_456|>",
3719
+ "lstrip": false,
3720
+ "normalized": false,
3721
+ "rstrip": false,
3722
+ "single_word": false,
3723
+ "special": true
3724
+ },
3725
+ "467": {
3726
+ "content": "<|reserved_457|>",
3727
+ "lstrip": false,
3728
+ "normalized": false,
3729
+ "rstrip": false,
3730
+ "single_word": false,
3731
+ "special": true
3732
+ },
3733
+ "468": {
3734
+ "content": "<|reserved_458|>",
3735
+ "lstrip": false,
3736
+ "normalized": false,
3737
+ "rstrip": false,
3738
+ "single_word": false,
3739
+ "special": true
3740
+ },
3741
+ "469": {
3742
+ "content": "<|reserved_459|>",
3743
+ "lstrip": false,
3744
+ "normalized": false,
3745
+ "rstrip": false,
3746
+ "single_word": false,
3747
+ "special": true
3748
+ },
3749
+ "470": {
3750
+ "content": "<|reserved_460|>",
3751
+ "lstrip": false,
3752
+ "normalized": false,
3753
+ "rstrip": false,
3754
+ "single_word": false,
3755
+ "special": true
3756
+ },
3757
+ "471": {
3758
+ "content": "<|reserved_461|>",
3759
+ "lstrip": false,
3760
+ "normalized": false,
3761
+ "rstrip": false,
3762
+ "single_word": false,
3763
+ "special": true
3764
+ },
3765
+ "472": {
3766
+ "content": "<|reserved_462|>",
3767
+ "lstrip": false,
3768
+ "normalized": false,
3769
+ "rstrip": false,
3770
+ "single_word": false,
3771
+ "special": true
3772
+ },
3773
+ "473": {
3774
+ "content": "<|reserved_463|>",
3775
+ "lstrip": false,
3776
+ "normalized": false,
3777
+ "rstrip": false,
3778
+ "single_word": false,
3779
+ "special": true
3780
+ },
3781
+ "474": {
3782
+ "content": "<|reserved_464|>",
3783
+ "lstrip": false,
3784
+ "normalized": false,
3785
+ "rstrip": false,
3786
+ "single_word": false,
3787
+ "special": true
3788
+ },
3789
+ "475": {
3790
+ "content": "<|reserved_465|>",
3791
+ "lstrip": false,
3792
+ "normalized": false,
3793
+ "rstrip": false,
3794
+ "single_word": false,
3795
+ "special": true
3796
+ },
3797
+ "476": {
3798
+ "content": "<|reserved_466|>",
3799
+ "lstrip": false,
3800
+ "normalized": false,
3801
+ "rstrip": false,
3802
+ "single_word": false,
3803
+ "special": true
3804
+ },
3805
+ "477": {
3806
+ "content": "<|reserved_467|>",
3807
+ "lstrip": false,
3808
+ "normalized": false,
3809
+ "rstrip": false,
3810
+ "single_word": false,
3811
+ "special": true
3812
+ },
3813
+ "478": {
3814
+ "content": "<|reserved_468|>",
3815
+ "lstrip": false,
3816
+ "normalized": false,
3817
+ "rstrip": false,
3818
+ "single_word": false,
3819
+ "special": true
3820
+ },
3821
+ "479": {
3822
+ "content": "<|reserved_469|>",
3823
+ "lstrip": false,
3824
+ "normalized": false,
3825
+ "rstrip": false,
3826
+ "single_word": false,
3827
+ "special": true
3828
+ },
3829
+ "480": {
3830
+ "content": "<|reserved_470|>",
3831
+ "lstrip": false,
3832
+ "normalized": false,
3833
+ "rstrip": false,
3834
+ "single_word": false,
3835
+ "special": true
3836
+ },
3837
+ "481": {
3838
+ "content": "<|reserved_471|>",
3839
+ "lstrip": false,
3840
+ "normalized": false,
3841
+ "rstrip": false,
3842
+ "single_word": false,
3843
+ "special": true
3844
+ },
3845
+ "482": {
3846
+ "content": "<|reserved_472|>",
3847
+ "lstrip": false,
3848
+ "normalized": false,
3849
+ "rstrip": false,
3850
+ "single_word": false,
3851
+ "special": true
3852
+ },
3853
+ "483": {
3854
+ "content": "<|reserved_473|>",
3855
+ "lstrip": false,
3856
+ "normalized": false,
3857
+ "rstrip": false,
3858
+ "single_word": false,
3859
+ "special": true
3860
+ },
3861
+ "484": {
3862
+ "content": "<|reserved_474|>",
3863
+ "lstrip": false,
3864
+ "normalized": false,
3865
+ "rstrip": false,
3866
+ "single_word": false,
3867
+ "special": true
3868
+ },
3869
+ "485": {
3870
+ "content": "<|reserved_475|>",
3871
+ "lstrip": false,
3872
+ "normalized": false,
3873
+ "rstrip": false,
3874
+ "single_word": false,
3875
+ "special": true
3876
+ },
3877
+ "486": {
3878
+ "content": "<|reserved_476|>",
3879
+ "lstrip": false,
3880
+ "normalized": false,
3881
+ "rstrip": false,
3882
+ "single_word": false,
3883
+ "special": true
3884
+ },
3885
+ "487": {
3886
+ "content": "<|reserved_477|>",
3887
+ "lstrip": false,
3888
+ "normalized": false,
3889
+ "rstrip": false,
3890
+ "single_word": false,
3891
+ "special": true
3892
+ },
3893
+ "488": {
3894
+ "content": "<|reserved_478|>",
3895
+ "lstrip": false,
3896
+ "normalized": false,
3897
+ "rstrip": false,
3898
+ "single_word": false,
3899
+ "special": true
3900
+ },
3901
+ "489": {
3902
+ "content": "<|reserved_479|>",
3903
+ "lstrip": false,
3904
+ "normalized": false,
3905
+ "rstrip": false,
3906
+ "single_word": false,
3907
+ "special": true
3908
+ },
3909
+ "490": {
3910
+ "content": "<|reserved_480|>",
3911
+ "lstrip": false,
3912
+ "normalized": false,
3913
+ "rstrip": false,
3914
+ "single_word": false,
3915
+ "special": true
3916
+ },
3917
+ "491": {
3918
+ "content": "<|reserved_481|>",
3919
+ "lstrip": false,
3920
+ "normalized": false,
3921
+ "rstrip": false,
3922
+ "single_word": false,
3923
+ "special": true
3924
+ },
3925
+ "492": {
3926
+ "content": "<|reserved_482|>",
3927
+ "lstrip": false,
3928
+ "normalized": false,
3929
+ "rstrip": false,
3930
+ "single_word": false,
3931
+ "special": true
3932
+ },
3933
+ "493": {
3934
+ "content": "<|reserved_483|>",
3935
+ "lstrip": false,
3936
+ "normalized": false,
3937
+ "rstrip": false,
3938
+ "single_word": false,
3939
+ "special": true
3940
+ },
3941
+ "494": {
3942
+ "content": "<|reserved_484|>",
3943
+ "lstrip": false,
3944
+ "normalized": false,
3945
+ "rstrip": false,
3946
+ "single_word": false,
3947
+ "special": true
3948
+ },
3949
+ "495": {
3950
+ "content": "<|reserved_485|>",
3951
+ "lstrip": false,
3952
+ "normalized": false,
3953
+ "rstrip": false,
3954
+ "single_word": false,
3955
+ "special": true
3956
+ },
3957
+ "496": {
3958
+ "content": "<|reserved_486|>",
3959
+ "lstrip": false,
3960
+ "normalized": false,
3961
+ "rstrip": false,
3962
+ "single_word": false,
3963
+ "special": true
3964
+ },
3965
+ "497": {
3966
+ "content": "<|reserved_487|>",
3967
+ "lstrip": false,
3968
+ "normalized": false,
3969
+ "rstrip": false,
3970
+ "single_word": false,
3971
+ "special": true
3972
+ },
3973
+ "498": {
3974
+ "content": "<|reserved_488|>",
3975
+ "lstrip": false,
3976
+ "normalized": false,
3977
+ "rstrip": false,
3978
+ "single_word": false,
3979
+ "special": true
3980
+ },
3981
+ "499": {
3982
+ "content": "<|reserved_489|>",
3983
+ "lstrip": false,
3984
+ "normalized": false,
3985
+ "rstrip": false,
3986
+ "single_word": false,
3987
+ "special": true
3988
+ },
3989
+ "500": {
3990
+ "content": "<|reserved_490|>",
3991
+ "lstrip": false,
3992
+ "normalized": false,
3993
+ "rstrip": false,
3994
+ "single_word": false,
3995
+ "special": true
3996
+ },
3997
+ "64011": {
3998
+ "content": "Mathias",
3999
+ "lstrip": false,
4000
+ "normalized": true,
4001
+ "rstrip": false,
4002
+ "single_word": false,
4003
+ "special": false
4004
+ },
4005
+ "64014": {
4006
+ "content": "python",
4007
+ "lstrip": false,
4008
+ "normalized": true,
4009
+ "rstrip": false,
4010
+ "single_word": false,
4011
+ "special": false
4012
+ },
4013
+ "64394": {
4014
+ "content": "<|cot_start|>",
4015
+ "lstrip": false,
4016
+ "normalized": false,
4017
+ "rstrip": false,
4018
+ "single_word": false,
4019
+ "special": true
4020
+ },
4021
+ "64395": {
4022
+ "content": "<|cot_end|>",
4023
+ "lstrip": false,
4024
+ "normalized": false,
4025
+ "rstrip": false,
4026
+ "single_word": false,
4027
+ "special": true
4028
+ },
4029
+ "64396": {
4030
+ "content": "<|review_start|>",
4031
+ "lstrip": false,
4032
+ "normalized": false,
4033
+ "rstrip": false,
4034
+ "single_word": false,
4035
+ "special": true
4036
+ },
4037
+ "64397": {
4038
+ "content": "<|review_end|>",
4039
+ "lstrip": false,
4040
+ "normalized": false,
4041
+ "rstrip": false,
4042
+ "single_word": false,
4043
+ "special": true
4044
+ },
4045
+ "64398": {
4046
+ "content": "<|file_start|>",
4047
+ "lstrip": false,
4048
+ "normalized": false,
4049
+ "rstrip": false,
4050
+ "single_word": false,
4051
+ "special": true
4052
+ },
4053
+ "64399": {
4054
+ "content": "<|file_end|>",
4055
+ "lstrip": false,
4056
+ "normalized": false,
4057
+ "rstrip": false,
4058
+ "single_word": false,
4059
+ "special": true
4060
+ }
4061
+ },
4062
+ "bos_token": "<|startoftext|>",
4063
+ "clean_up_tokenization_spaces": true,
4064
+ "eos_token": "<|im_end|>",
4065
+ "extra_special_tokens": {},
4066
+ "legacy": false,
4067
+ "model_max_length": 1000000000000000019884624838656,
4068
+ "model_input_names": [
4069
+ "input_ids",
4070
+ "attention_mask"
4071
+ ],
4072
+ "pad_token": "<|pad|>",
4073
+ "sp_model_kwargs": {},
4074
+ "spaces_between_special_tokens": false,
4075
+ "tokenizer_class": "PreTrainedTokenizerFast",
4076
+ "unk_token": "<|endoftext|>",
4077
+ "use_default_system_prompt": false,
4078
+ "use_fast": true
4079
+ }
ud.py ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import numpy
2
+ from transformers import TokenClassificationPipeline
3
+
4
+ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
5
+ def __init__(self,**kwargs):
6
+ from copy import deepcopy
7
+ from tokenizers import Regex
8
+ from tokenizers.pre_tokenizers import Sequence,Split,Whitespace,Punctuation
9
+ super().__init__(**kwargs)
10
+ self.oldtokenizer=deepcopy(self.tokenizer)
11
+ self.tokenizer.backend_tokenizer.pre_tokenizer=Sequence([Split(Regex("[ぁ-ん]"),"isolated"),Whitespace(),Punctuation(),self.oldtokenizer.backend_tokenizer.pre_tokenizer])
12
+ x=self.model.config.label2id
13
+ y=[k for k in x if k.find("|")<0 and not k.startswith("I-")]
14
+ self.transition=numpy.full((len(x),len(x)),-numpy.inf)
15
+ self.sympos=numpy.full((len(x)),-numpy.inf)
16
+ for k,v in x.items():
17
+ if k.find("|")<0:
18
+ for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
19
+ self.transition[v,x[j]]=0
20
+ if k.startswith("SYM"):
21
+ self.sympos[v]=0
22
+ def check_model_type(self,supported_models):
23
+ pass
24
+ def postprocess(self,model_outputs,**kwargs):
25
+ if "logits" not in model_outputs:
26
+ return self.postprocess(model_outputs[0],**kwargs)
27
+ return self.bellman_ford_token_classification(model_outputs,**kwargs)
28
+ def bellman_ford_token_classification(self,model_outputs,**kwargs):
29
+ m=model_outputs["logits"][0].numpy()
30
+ v=model_outputs["offset_mapping"][0].tolist()
31
+ e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
32
+ z=e/e.sum(axis=-1,keepdims=True)
33
+ for i in range(m.shape[0]-1,0,-1):
34
+ if v[i-1][0]<v[i-1][1]:
35
+ m[i-1]+=numpy.max(m[i]+self.transition,axis=1)
36
+ else:
37
+ m[i-1]+=self.sympos
38
+ k=[numpy.argmax(m[0]+self.transition[0])]
39
+ for i in range(1,m.shape[0]):
40
+ k.append(numpy.argmax(m[i]+self.transition[k[-1]]))
41
+ w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(v,k)) if s<e]
42
+ if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
43
+ for i,t in reversed(list(enumerate(w))):
44
+ p=t.pop("entity")
45
+ if p.startswith("I-"):
46
+ w[i-1]["score"]=min(w[i-1]["score"],t["score"])
47
+ w[i-1]["end"]=w.pop(i)["end"]
48
+ elif i>0 and w[i-1]["end"]>t["start"]:
49
+ w[i-1]["score"]=min(w[i-1]["score"],t["score"])
50
+ w[i-1]["end"]=w.pop(i)["end"]
51
+ elif p.startswith("B-"):
52
+ t["entity_group"]=p[2:]
53
+ else:
54
+ t["entity_group"]=p
55
+ for t in w:
56
+ t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
57
+ return w
58
+
59
+ class UniversalDependenciesPipeline(BellmanFordTokenClassificationPipeline):
60
+ def __init__(self,**kwargs):
61
+ kwargs["aggregation_strategy"]="simple"
62
+ super().__init__(**kwargs)
63
+ x=self.model.config.label2id
64
+ self.root=numpy.full((len(x)),-numpy.inf)
65
+ self.left_arc=numpy.full((len(x)),-numpy.inf)
66
+ self.right_arc=numpy.full((len(x)),-numpy.inf)
67
+ for k,v in x.items():
68
+ if k.endswith("|root"):
69
+ self.root[v]=0
70
+ elif k.find("|l-")>0:
71
+ self.left_arc[v]=0
72
+ elif k.find("|r-")>0:
73
+ self.right_arc[v]=0
74
+ def postprocess(self,model_outputs,**kwargs):
75
+ import torch
76
+ kwargs["aggregation_strategy"]="simple"
77
+ if "logits" not in model_outputs:
78
+ return self.postprocess(model_outputs[0],**kwargs)
79
+ w=self.bellman_ford_token_classification(model_outputs,**kwargs)
80
+ off=[(t["start"],t["end"]) for t in w]
81
+ for i,(s,e) in reversed(list(enumerate(off))):
82
+ if s<e:
83
+ d=w[i]["text"]
84
+ j=len(d)-len(d.lstrip())
85
+ if j>0:
86
+ d=d.lstrip()
87
+ off[i]=(off[i][0]+j,off[i][1])
88
+ j=len(d)-len(d.rstrip())
89
+ if j>0:
90
+ d=d.rstrip()
91
+ off[i]=(off[i][0],off[i][1]-j)
92
+ if d.strip()=="":
93
+ off.pop(i)
94
+ w.pop(i)
95
+ v=self.oldtokenizer([t["text"] for t in w],add_special_tokens=False)
96
+ x=[not t["entity_group"].endswith(".") for t in w]
97
+ z=model_outputs["input_ids"][0]
98
+ if len(x)<504:
99
+ x=[True]*len(x)
100
+ else:
101
+ k=sum([len(x)-i+1 if b else 0 for i,b in enumerate(x)])+len(z)+1
102
+ for i in numpy.argsort(numpy.array([t["score"] for t in w])):
103
+ if x[i]==False and k+len(x)-i<128000:
104
+ x[i]=True
105
+ k+=len(x)-i+1
106
+ ids=[-1]
107
+ for i in range(len(x)):
108
+ if x[i]:
109
+ ids.append(i)
110
+ for j in range(i+1,len(x)):
111
+ ids.append(j)
112
+ ids.append(-1)
113
+ with torch.no_grad():
114
+ e=self.model.get_input_embeddings().weight
115
+ m=[]
116
+ for j in v["input_ids"]:
117
+ if j==[]:
118
+ j=[self.tokenizer.unk_token_id]
119
+ m.append(e[j,:].sum(axis=0))
120
+ m.append(e[self.tokenizer.eos_token_id,:])
121
+ m=torch.stack(m).to(self.device)
122
+ e=self.model(inputs_embeds=torch.unsqueeze(torch.vstack((e[z,:],m[ids,:])),0))
123
+ m=e.logits[0].cpu().numpy()
124
+ e=numpy.full((len(x),len(x),m.shape[-1]),m.min())
125
+ k=len(z)+1
126
+ for i in range(len(x)):
127
+ if x[i]:
128
+ e[i,i]=m[k]+self.root
129
+ k+=1
130
+ for j in range(1,len(x)-i):
131
+ e[i+j,i]=m[k]+self.left_arc
132
+ e[i,i+j]=m[k]+self.right_arc
133
+ k+=1
134
+ k+=1
135
+ m,p=numpy.max(e,axis=2),numpy.argmax(e,axis=2)
136
+ h=self.chu_liu_edmonds(m)
137
+ z=[i for i,j in enumerate(h) if i==j]
138
+ if len(z)>1:
139
+ k,h=z[numpy.argmax(m[z,z])],numpy.min(m)-numpy.max(m)
140
+ m[:,z]+=[[0 if j in z and (i!=j or i==k) else h for i in z] for j in range(m.shape[0])]
141
+ h=self.chu_liu_edmonds(m)
142
+ q=[self.model.config.id2label[p[j,i]].split("|") for i,j in enumerate(h)]
143
+ t=model_outputs["sentence"].replace("\n"," ")
144
+ u="# text = "+t+"\n"
145
+ for i,(s,e) in enumerate(off):
146
+ u+="\t".join([str(i+1),t[s:e],"_",q[i][0],"_","_" if len(q[i])<3 else "|".join(q[i][1:-1]),str(0 if h[i]==i else h[i]+1),"root" if q[i][-1]=="root" else q[i][-1][2:],"_","_" if i+1<len(off) and e<off[i+1][0] else "SpaceAfter=No"])+"\n"
147
+ return u+"\n"
148
+ def chu_liu_edmonds(self,matrix):
149
+ h=numpy.argmax(matrix,axis=0)
150
+ x=[-1 if i==j else j for i,j in enumerate(h)]
151
+ for b in [lambda x,i,j:-1 if i not in x else x[i],lambda x,i,j:-1 if j<0 else x[j]]:
152
+ y=[]
153
+ while x!=y:
154
+ y=list(x)
155
+ for i,j in enumerate(x):
156
+ x[i]=b(x,i,j)
157
+ if max(x)<0:
158
+ return h
159
+ y,x=[i for i,j in enumerate(x) if j==max(x)],[i for i,j in enumerate(x) if j<max(x)]
160
+ z=matrix-numpy.max(matrix,axis=0)
161
+ m=numpy.block([[z[x,:][:,x],numpy.max(z[x,:][:,y],axis=1).reshape(len(x),1)],[numpy.max(z[y,:][:,x],axis=0),numpy.max(z[y,y])]])
162
+ k=[j if i==len(x) else x[j] if j<len(x) else y[numpy.argmax(z[y,x[i]])] for i,j in enumerate(self.chu_liu_edmonds(m))]
163
+ h=[j if i in y else k[x.index(i)] for i,j in enumerate(h)]
164
+ i=y[numpy.argmax(z[x[k[-1]],y] if k[-1]<len(x) else z[y,y])]
165
+ h[i]=x[k[-1]] if k[-1]<len(x) else i
166
+ return h