bbunzeck commited on
Commit
6b80a2a
·
verified ·
1 Parent(s): b48396b

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 256,
14
+ "max_position_embeddings": 256,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 8,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 1,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-06,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.46.3",
28
+ "use_cache": true,
29
+ "vocab_size": 110
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.46.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390715f0b2da0ea655da008f4bb951a16fac945dd71f46ab329a73ce00b606f5
3
+ size 14930768
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c193dbb8863512e24018668a9aaab046501a0339b79ee1cd22202d5b4d733f39
3
+ size 29906938
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:013d13e4b269a8648da58d2f40bf48e004388ea0631771b8c8e588ab75375092
3
+ size 13990
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0095c7056fa6f1394c329e00794ee91b0ee818435ef217c1ef38db4cdde9de0b
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,1025 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 0,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<|endoftext|>"
16
+ },
17
+ "added_tokens": [
18
+ {
19
+ "id": 0,
20
+ "content": "<|endoftext|>",
21
+ "single_word": false,
22
+ "lstrip": false,
23
+ "rstrip": false,
24
+ "normalized": false,
25
+ "special": true
26
+ },
27
+ {
28
+ "id": 1,
29
+ "content": "<pad>",
30
+ "single_word": false,
31
+ "lstrip": false,
32
+ "rstrip": false,
33
+ "normalized": false,
34
+ "special": true
35
+ },
36
+ {
37
+ "id": 2,
38
+ "content": "0",
39
+ "single_word": false,
40
+ "lstrip": false,
41
+ "rstrip": false,
42
+ "normalized": true,
43
+ "special": false
44
+ },
45
+ {
46
+ "id": 3,
47
+ "content": "1",
48
+ "single_word": false,
49
+ "lstrip": false,
50
+ "rstrip": false,
51
+ "normalized": true,
52
+ "special": false
53
+ },
54
+ {
55
+ "id": 4,
56
+ "content": "2",
57
+ "single_word": false,
58
+ "lstrip": false,
59
+ "rstrip": false,
60
+ "normalized": true,
61
+ "special": false
62
+ },
63
+ {
64
+ "id": 5,
65
+ "content": "3",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": true,
70
+ "special": false
71
+ },
72
+ {
73
+ "id": 6,
74
+ "content": "4",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": true,
79
+ "special": false
80
+ },
81
+ {
82
+ "id": 7,
83
+ "content": "5",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": true,
88
+ "special": false
89
+ },
90
+ {
91
+ "id": 8,
92
+ "content": "6",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": true,
97
+ "special": false
98
+ },
99
+ {
100
+ "id": 9,
101
+ "content": "7",
102
+ "single_word": false,
103
+ "lstrip": false,
104
+ "rstrip": false,
105
+ "normalized": true,
106
+ "special": false
107
+ },
108
+ {
109
+ "id": 10,
110
+ "content": "8",
111
+ "single_word": false,
112
+ "lstrip": false,
113
+ "rstrip": false,
114
+ "normalized": true,
115
+ "special": false
116
+ },
117
+ {
118
+ "id": 11,
119
+ "content": "9",
120
+ "single_word": false,
121
+ "lstrip": false,
122
+ "rstrip": false,
123
+ "normalized": true,
124
+ "special": false
125
+ },
126
+ {
127
+ "id": 12,
128
+ "content": "a",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": true,
133
+ "special": false
134
+ },
135
+ {
136
+ "id": 13,
137
+ "content": "b",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": true,
142
+ "special": false
143
+ },
144
+ {
145
+ "id": 14,
146
+ "content": "c",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": true,
151
+ "special": false
152
+ },
153
+ {
154
+ "id": 15,
155
+ "content": "d",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": true,
160
+ "special": false
161
+ },
162
+ {
163
+ "id": 16,
164
+ "content": "e",
165
+ "single_word": false,
166
+ "lstrip": false,
167
+ "rstrip": false,
168
+ "normalized": true,
169
+ "special": false
170
+ },
171
+ {
172
+ "id": 17,
173
+ "content": "f",
174
+ "single_word": false,
175
+ "lstrip": false,
176
+ "rstrip": false,
177
+ "normalized": true,
178
+ "special": false
179
+ },
180
+ {
181
+ "id": 18,
182
+ "content": "g",
183
+ "single_word": false,
184
+ "lstrip": false,
185
+ "rstrip": false,
186
+ "normalized": true,
187
+ "special": false
188
+ },
189
+ {
190
+ "id": 19,
191
+ "content": "h",
192
+ "single_word": false,
193
+ "lstrip": false,
194
+ "rstrip": false,
195
+ "normalized": true,
196
+ "special": false
197
+ },
198
+ {
199
+ "id": 20,
200
+ "content": "i",
201
+ "single_word": false,
202
+ "lstrip": false,
203
+ "rstrip": false,
204
+ "normalized": true,
205
+ "special": false
206
+ },
207
+ {
208
+ "id": 21,
209
+ "content": "j",
210
+ "single_word": false,
211
+ "lstrip": false,
212
+ "rstrip": false,
213
+ "normalized": true,
214
+ "special": false
215
+ },
216
+ {
217
+ "id": 22,
218
+ "content": "k",
219
+ "single_word": false,
220
+ "lstrip": false,
221
+ "rstrip": false,
222
+ "normalized": true,
223
+ "special": false
224
+ },
225
+ {
226
+ "id": 23,
227
+ "content": "l",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": true,
232
+ "special": false
233
+ },
234
+ {
235
+ "id": 24,
236
+ "content": "m",
237
+ "single_word": false,
238
+ "lstrip": false,
239
+ "rstrip": false,
240
+ "normalized": true,
241
+ "special": false
242
+ },
243
+ {
244
+ "id": 25,
245
+ "content": "n",
246
+ "single_word": false,
247
+ "lstrip": false,
248
+ "rstrip": false,
249
+ "normalized": true,
250
+ "special": false
251
+ },
252
+ {
253
+ "id": 26,
254
+ "content": "o",
255
+ "single_word": false,
256
+ "lstrip": false,
257
+ "rstrip": false,
258
+ "normalized": true,
259
+ "special": false
260
+ },
261
+ {
262
+ "id": 27,
263
+ "content": "p",
264
+ "single_word": false,
265
+ "lstrip": false,
266
+ "rstrip": false,
267
+ "normalized": true,
268
+ "special": false
269
+ },
270
+ {
271
+ "id": 28,
272
+ "content": "q",
273
+ "single_word": false,
274
+ "lstrip": false,
275
+ "rstrip": false,
276
+ "normalized": true,
277
+ "special": false
278
+ },
279
+ {
280
+ "id": 29,
281
+ "content": "r",
282
+ "single_word": false,
283
+ "lstrip": false,
284
+ "rstrip": false,
285
+ "normalized": true,
286
+ "special": false
287
+ },
288
+ {
289
+ "id": 30,
290
+ "content": "s",
291
+ "single_word": false,
292
+ "lstrip": false,
293
+ "rstrip": false,
294
+ "normalized": true,
295
+ "special": false
296
+ },
297
+ {
298
+ "id": 31,
299
+ "content": "t",
300
+ "single_word": false,
301
+ "lstrip": false,
302
+ "rstrip": false,
303
+ "normalized": true,
304
+ "special": false
305
+ },
306
+ {
307
+ "id": 32,
308
+ "content": "u",
309
+ "single_word": false,
310
+ "lstrip": false,
311
+ "rstrip": false,
312
+ "normalized": true,
313
+ "special": false
314
+ },
315
+ {
316
+ "id": 33,
317
+ "content": "v",
318
+ "single_word": false,
319
+ "lstrip": false,
320
+ "rstrip": false,
321
+ "normalized": true,
322
+ "special": false
323
+ },
324
+ {
325
+ "id": 34,
326
+ "content": "w",
327
+ "single_word": false,
328
+ "lstrip": false,
329
+ "rstrip": false,
330
+ "normalized": true,
331
+ "special": false
332
+ },
333
+ {
334
+ "id": 35,
335
+ "content": "x",
336
+ "single_word": false,
337
+ "lstrip": false,
338
+ "rstrip": false,
339
+ "normalized": true,
340
+ "special": false
341
+ },
342
+ {
343
+ "id": 36,
344
+ "content": "y",
345
+ "single_word": false,
346
+ "lstrip": false,
347
+ "rstrip": false,
348
+ "normalized": true,
349
+ "special": false
350
+ },
351
+ {
352
+ "id": 37,
353
+ "content": "z",
354
+ "single_word": false,
355
+ "lstrip": false,
356
+ "rstrip": false,
357
+ "normalized": true,
358
+ "special": false
359
+ },
360
+ {
361
+ "id": 38,
362
+ "content": "A",
363
+ "single_word": false,
364
+ "lstrip": false,
365
+ "rstrip": false,
366
+ "normalized": true,
367
+ "special": false
368
+ },
369
+ {
370
+ "id": 39,
371
+ "content": "B",
372
+ "single_word": false,
373
+ "lstrip": false,
374
+ "rstrip": false,
375
+ "normalized": true,
376
+ "special": false
377
+ },
378
+ {
379
+ "id": 40,
380
+ "content": "C",
381
+ "single_word": false,
382
+ "lstrip": false,
383
+ "rstrip": false,
384
+ "normalized": true,
385
+ "special": false
386
+ },
387
+ {
388
+ "id": 41,
389
+ "content": "D",
390
+ "single_word": false,
391
+ "lstrip": false,
392
+ "rstrip": false,
393
+ "normalized": true,
394
+ "special": false
395
+ },
396
+ {
397
+ "id": 42,
398
+ "content": "E",
399
+ "single_word": false,
400
+ "lstrip": false,
401
+ "rstrip": false,
402
+ "normalized": true,
403
+ "special": false
404
+ },
405
+ {
406
+ "id": 43,
407
+ "content": "F",
408
+ "single_word": false,
409
+ "lstrip": false,
410
+ "rstrip": false,
411
+ "normalized": true,
412
+ "special": false
413
+ },
414
+ {
415
+ "id": 44,
416
+ "content": "G",
417
+ "single_word": false,
418
+ "lstrip": false,
419
+ "rstrip": false,
420
+ "normalized": true,
421
+ "special": false
422
+ },
423
+ {
424
+ "id": 45,
425
+ "content": "H",
426
+ "single_word": false,
427
+ "lstrip": false,
428
+ "rstrip": false,
429
+ "normalized": true,
430
+ "special": false
431
+ },
432
+ {
433
+ "id": 46,
434
+ "content": "I",
435
+ "single_word": false,
436
+ "lstrip": false,
437
+ "rstrip": false,
438
+ "normalized": true,
439
+ "special": false
440
+ },
441
+ {
442
+ "id": 47,
443
+ "content": "J",
444
+ "single_word": false,
445
+ "lstrip": false,
446
+ "rstrip": false,
447
+ "normalized": true,
448
+ "special": false
449
+ },
450
+ {
451
+ "id": 48,
452
+ "content": "K",
453
+ "single_word": false,
454
+ "lstrip": false,
455
+ "rstrip": false,
456
+ "normalized": true,
457
+ "special": false
458
+ },
459
+ {
460
+ "id": 49,
461
+ "content": "L",
462
+ "single_word": false,
463
+ "lstrip": false,
464
+ "rstrip": false,
465
+ "normalized": true,
466
+ "special": false
467
+ },
468
+ {
469
+ "id": 50,
470
+ "content": "M",
471
+ "single_word": false,
472
+ "lstrip": false,
473
+ "rstrip": false,
474
+ "normalized": true,
475
+ "special": false
476
+ },
477
+ {
478
+ "id": 51,
479
+ "content": "N",
480
+ "single_word": false,
481
+ "lstrip": false,
482
+ "rstrip": false,
483
+ "normalized": true,
484
+ "special": false
485
+ },
486
+ {
487
+ "id": 52,
488
+ "content": "O",
489
+ "single_word": false,
490
+ "lstrip": false,
491
+ "rstrip": false,
492
+ "normalized": true,
493
+ "special": false
494
+ },
495
+ {
496
+ "id": 53,
497
+ "content": "P",
498
+ "single_word": false,
499
+ "lstrip": false,
500
+ "rstrip": false,
501
+ "normalized": true,
502
+ "special": false
503
+ },
504
+ {
505
+ "id": 54,
506
+ "content": "Q",
507
+ "single_word": false,
508
+ "lstrip": false,
509
+ "rstrip": false,
510
+ "normalized": true,
511
+ "special": false
512
+ },
513
+ {
514
+ "id": 55,
515
+ "content": "R",
516
+ "single_word": false,
517
+ "lstrip": false,
518
+ "rstrip": false,
519
+ "normalized": true,
520
+ "special": false
521
+ },
522
+ {
523
+ "id": 56,
524
+ "content": "S",
525
+ "single_word": false,
526
+ "lstrip": false,
527
+ "rstrip": false,
528
+ "normalized": true,
529
+ "special": false
530
+ },
531
+ {
532
+ "id": 57,
533
+ "content": "T",
534
+ "single_word": false,
535
+ "lstrip": false,
536
+ "rstrip": false,
537
+ "normalized": true,
538
+ "special": false
539
+ },
540
+ {
541
+ "id": 58,
542
+ "content": "U",
543
+ "single_word": false,
544
+ "lstrip": false,
545
+ "rstrip": false,
546
+ "normalized": true,
547
+ "special": false
548
+ },
549
+ {
550
+ "id": 59,
551
+ "content": "V",
552
+ "single_word": false,
553
+ "lstrip": false,
554
+ "rstrip": false,
555
+ "normalized": true,
556
+ "special": false
557
+ },
558
+ {
559
+ "id": 60,
560
+ "content": "W",
561
+ "single_word": false,
562
+ "lstrip": false,
563
+ "rstrip": false,
564
+ "normalized": true,
565
+ "special": false
566
+ },
567
+ {
568
+ "id": 61,
569
+ "content": "X",
570
+ "single_word": false,
571
+ "lstrip": false,
572
+ "rstrip": false,
573
+ "normalized": true,
574
+ "special": false
575
+ },
576
+ {
577
+ "id": 62,
578
+ "content": "Y",
579
+ "single_word": false,
580
+ "lstrip": false,
581
+ "rstrip": false,
582
+ "normalized": true,
583
+ "special": false
584
+ },
585
+ {
586
+ "id": 63,
587
+ "content": "Z",
588
+ "single_word": false,
589
+ "lstrip": false,
590
+ "rstrip": false,
591
+ "normalized": true,
592
+ "special": false
593
+ },
594
+ {
595
+ "id": 64,
596
+ "content": "!",
597
+ "single_word": false,
598
+ "lstrip": false,
599
+ "rstrip": false,
600
+ "normalized": true,
601
+ "special": false
602
+ },
603
+ {
604
+ "id": 65,
605
+ "content": "\"",
606
+ "single_word": false,
607
+ "lstrip": false,
608
+ "rstrip": false,
609
+ "normalized": true,
610
+ "special": false
611
+ },
612
+ {
613
+ "id": 66,
614
+ "content": "#",
615
+ "single_word": false,
616
+ "lstrip": false,
617
+ "rstrip": false,
618
+ "normalized": true,
619
+ "special": false
620
+ },
621
+ {
622
+ "id": 67,
623
+ "content": "$",
624
+ "single_word": false,
625
+ "lstrip": false,
626
+ "rstrip": false,
627
+ "normalized": true,
628
+ "special": false
629
+ },
630
+ {
631
+ "id": 68,
632
+ "content": "%",
633
+ "single_word": false,
634
+ "lstrip": false,
635
+ "rstrip": false,
636
+ "normalized": true,
637
+ "special": false
638
+ },
639
+ {
640
+ "id": 69,
641
+ "content": "&",
642
+ "single_word": false,
643
+ "lstrip": false,
644
+ "rstrip": false,
645
+ "normalized": true,
646
+ "special": false
647
+ },
648
+ {
649
+ "id": 70,
650
+ "content": "'",
651
+ "single_word": false,
652
+ "lstrip": false,
653
+ "rstrip": false,
654
+ "normalized": true,
655
+ "special": false
656
+ },
657
+ {
658
+ "id": 71,
659
+ "content": "(",
660
+ "single_word": false,
661
+ "lstrip": false,
662
+ "rstrip": false,
663
+ "normalized": true,
664
+ "special": false
665
+ },
666
+ {
667
+ "id": 72,
668
+ "content": ")",
669
+ "single_word": false,
670
+ "lstrip": false,
671
+ "rstrip": false,
672
+ "normalized": true,
673
+ "special": false
674
+ },
675
+ {
676
+ "id": 73,
677
+ "content": "*",
678
+ "single_word": false,
679
+ "lstrip": false,
680
+ "rstrip": false,
681
+ "normalized": true,
682
+ "special": false
683
+ },
684
+ {
685
+ "id": 74,
686
+ "content": "+",
687
+ "single_word": false,
688
+ "lstrip": false,
689
+ "rstrip": false,
690
+ "normalized": true,
691
+ "special": false
692
+ },
693
+ {
694
+ "id": 75,
695
+ "content": ",",
696
+ "single_word": false,
697
+ "lstrip": false,
698
+ "rstrip": false,
699
+ "normalized": true,
700
+ "special": false
701
+ },
702
+ {
703
+ "id": 76,
704
+ "content": "-",
705
+ "single_word": false,
706
+ "lstrip": false,
707
+ "rstrip": false,
708
+ "normalized": true,
709
+ "special": false
710
+ },
711
+ {
712
+ "id": 77,
713
+ "content": ".",
714
+ "single_word": false,
715
+ "lstrip": false,
716
+ "rstrip": false,
717
+ "normalized": true,
718
+ "special": false
719
+ },
720
+ {
721
+ "id": 78,
722
+ "content": "/",
723
+ "single_word": false,
724
+ "lstrip": false,
725
+ "rstrip": false,
726
+ "normalized": true,
727
+ "special": false
728
+ },
729
+ {
730
+ "id": 79,
731
+ "content": ":",
732
+ "single_word": false,
733
+ "lstrip": false,
734
+ "rstrip": false,
735
+ "normalized": true,
736
+ "special": false
737
+ },
738
+ {
739
+ "id": 80,
740
+ "content": ";",
741
+ "single_word": false,
742
+ "lstrip": false,
743
+ "rstrip": false,
744
+ "normalized": true,
745
+ "special": false
746
+ },
747
+ {
748
+ "id": 81,
749
+ "content": "<",
750
+ "single_word": false,
751
+ "lstrip": false,
752
+ "rstrip": false,
753
+ "normalized": true,
754
+ "special": false
755
+ },
756
+ {
757
+ "id": 82,
758
+ "content": "=",
759
+ "single_word": false,
760
+ "lstrip": false,
761
+ "rstrip": false,
762
+ "normalized": true,
763
+ "special": false
764
+ },
765
+ {
766
+ "id": 83,
767
+ "content": ">",
768
+ "single_word": false,
769
+ "lstrip": false,
770
+ "rstrip": false,
771
+ "normalized": true,
772
+ "special": false
773
+ },
774
+ {
775
+ "id": 84,
776
+ "content": "?",
777
+ "single_word": false,
778
+ "lstrip": false,
779
+ "rstrip": false,
780
+ "normalized": true,
781
+ "special": false
782
+ },
783
+ {
784
+ "id": 85,
785
+ "content": "@",
786
+ "single_word": false,
787
+ "lstrip": false,
788
+ "rstrip": false,
789
+ "normalized": true,
790
+ "special": false
791
+ },
792
+ {
793
+ "id": 86,
794
+ "content": "[",
795
+ "single_word": false,
796
+ "lstrip": false,
797
+ "rstrip": false,
798
+ "normalized": true,
799
+ "special": false
800
+ },
801
+ {
802
+ "id": 87,
803
+ "content": "\\",
804
+ "single_word": false,
805
+ "lstrip": false,
806
+ "rstrip": false,
807
+ "normalized": true,
808
+ "special": false
809
+ },
810
+ {
811
+ "id": 88,
812
+ "content": "]",
813
+ "single_word": false,
814
+ "lstrip": false,
815
+ "rstrip": false,
816
+ "normalized": true,
817
+ "special": false
818
+ },
819
+ {
820
+ "id": 89,
821
+ "content": "^",
822
+ "single_word": false,
823
+ "lstrip": false,
824
+ "rstrip": false,
825
+ "normalized": true,
826
+ "special": false
827
+ },
828
+ {
829
+ "id": 90,
830
+ "content": "_",
831
+ "single_word": false,
832
+ "lstrip": false,
833
+ "rstrip": false,
834
+ "normalized": true,
835
+ "special": false
836
+ },
837
+ {
838
+ "id": 91,
839
+ "content": "`",
840
+ "single_word": false,
841
+ "lstrip": false,
842
+ "rstrip": false,
843
+ "normalized": true,
844
+ "special": false
845
+ },
846
+ {
847
+ "id": 92,
848
+ "content": "{",
849
+ "single_word": false,
850
+ "lstrip": false,
851
+ "rstrip": false,
852
+ "normalized": true,
853
+ "special": false
854
+ },
855
+ {
856
+ "id": 93,
857
+ "content": "|",
858
+ "single_word": false,
859
+ "lstrip": false,
860
+ "rstrip": false,
861
+ "normalized": true,
862
+ "special": false
863
+ },
864
+ {
865
+ "id": 94,
866
+ "content": "}",
867
+ "single_word": false,
868
+ "lstrip": false,
869
+ "rstrip": false,
870
+ "normalized": true,
871
+ "special": false
872
+ },
873
+ {
874
+ "id": 95,
875
+ "content": "~",
876
+ "single_word": false,
877
+ "lstrip": false,
878
+ "rstrip": false,
879
+ "normalized": true,
880
+ "special": false
881
+ },
882
+ {
883
+ "id": 96,
884
+ "content": " ",
885
+ "single_word": false,
886
+ "lstrip": false,
887
+ "rstrip": false,
888
+ "normalized": true,
889
+ "special": false
890
+ },
891
+ {
892
+ "id": 97,
893
+ "content": "\t",
894
+ "single_word": false,
895
+ "lstrip": false,
896
+ "rstrip": false,
897
+ "normalized": true,
898
+ "special": false
899
+ },
900
+ {
901
+ "id": 98,
902
+ "content": "\n",
903
+ "single_word": false,
904
+ "lstrip": false,
905
+ "rstrip": false,
906
+ "normalized": true,
907
+ "special": false
908
+ },
909
+ {
910
+ "id": 99,
911
+ "content": "\r",
912
+ "single_word": false,
913
+ "lstrip": false,
914
+ "rstrip": false,
915
+ "normalized": true,
916
+ "special": false
917
+ },
918
+ {
919
+ "id": 100,
920
+ "content": "\u000b",
921
+ "single_word": false,
922
+ "lstrip": false,
923
+ "rstrip": false,
924
+ "normalized": true,
925
+ "special": false
926
+ },
927
+ {
928
+ "id": 101,
929
+ "content": "\f",
930
+ "single_word": false,
931
+ "lstrip": false,
932
+ "rstrip": false,
933
+ "normalized": true,
934
+ "special": false
935
+ },
936
+ {
937
+ "id": 102,
938
+ "content": "ö",
939
+ "single_word": false,
940
+ "lstrip": false,
941
+ "rstrip": false,
942
+ "normalized": true,
943
+ "special": false
944
+ },
945
+ {
946
+ "id": 103,
947
+ "content": "Ö",
948
+ "single_word": false,
949
+ "lstrip": false,
950
+ "rstrip": false,
951
+ "normalized": true,
952
+ "special": false
953
+ },
954
+ {
955
+ "id": 104,
956
+ "content": "ä",
957
+ "single_word": false,
958
+ "lstrip": false,
959
+ "rstrip": false,
960
+ "normalized": true,
961
+ "special": false
962
+ },
963
+ {
964
+ "id": 105,
965
+ "content": "Ä",
966
+ "single_word": false,
967
+ "lstrip": false,
968
+ "rstrip": false,
969
+ "normalized": true,
970
+ "special": false
971
+ },
972
+ {
973
+ "id": 106,
974
+ "content": "ü",
975
+ "single_word": false,
976
+ "lstrip": false,
977
+ "rstrip": false,
978
+ "normalized": true,
979
+ "special": false
980
+ },
981
+ {
982
+ "id": 107,
983
+ "content": "Ü",
984
+ "single_word": false,
985
+ "lstrip": false,
986
+ "rstrip": false,
987
+ "normalized": true,
988
+ "special": false
989
+ },
990
+ {
991
+ "id": 108,
992
+ "content": "ß",
993
+ "single_word": false,
994
+ "lstrip": false,
995
+ "rstrip": false,
996
+ "normalized": true,
997
+ "special": false
998
+ },
999
+ {
1000
+ "id": 109,
1001
+ "content": "ẞ",
1002
+ "single_word": false,
1003
+ "lstrip": false,
1004
+ "rstrip": false,
1005
+ "normalized": true,
1006
+ "special": false
1007
+ }
1008
+ ],
1009
+ "normalizer": null,
1010
+ "pre_tokenizer": null,
1011
+ "post_processor": null,
1012
+ "decoder": null,
1013
+ "model": {
1014
+ "type": "BPE",
1015
+ "dropout": null,
1016
+ "unk_token": null,
1017
+ "continuing_subword_prefix": null,
1018
+ "end_of_word_suffix": null,
1019
+ "fuse_unk": false,
1020
+ "byte_fallback": false,
1021
+ "ignore_merges": false,
1022
+ "vocab": {},
1023
+ "merges": []
1024
+ }
1025
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "0",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "1",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "4": {
36
+ "content": "2",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "3",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "4",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "5",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "6",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "7",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "8",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "9",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "a",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": "b",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "c",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "d",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": "e",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "f",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "18": {
148
+ "content": "g",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "19": {
156
+ "content": "h",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "20": {
164
+ "content": "i",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "21": {
172
+ "content": "j",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "22": {
180
+ "content": "k",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "23": {
188
+ "content": "l",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "24": {
196
+ "content": "m",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "25": {
204
+ "content": "n",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "26": {
212
+ "content": "o",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "27": {
220
+ "content": "p",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "28": {
228
+ "content": "q",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "29": {
236
+ "content": "r",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "30": {
244
+ "content": "s",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "31": {
252
+ "content": "t",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "32": {
260
+ "content": "u",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "33": {
268
+ "content": "v",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "34": {
276
+ "content": "w",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "35": {
284
+ "content": "x",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "36": {
292
+ "content": "y",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "37": {
300
+ "content": "z",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "38": {
308
+ "content": "A",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "39": {
316
+ "content": "B",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "40": {
324
+ "content": "C",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "41": {
332
+ "content": "D",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "42": {
340
+ "content": "E",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "43": {
348
+ "content": "F",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "44": {
356
+ "content": "G",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "45": {
364
+ "content": "H",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "46": {
372
+ "content": "I",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "47": {
380
+ "content": "J",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "48": {
388
+ "content": "K",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "49": {
396
+ "content": "L",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50": {
404
+ "content": "M",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "51": {
412
+ "content": "N",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "52": {
420
+ "content": "O",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "53": {
428
+ "content": "P",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "54": {
436
+ "content": "Q",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "55": {
444
+ "content": "R",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "56": {
452
+ "content": "S",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "57": {
460
+ "content": "T",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "58": {
468
+ "content": "U",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "59": {
476
+ "content": "V",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "60": {
484
+ "content": "W",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "61": {
492
+ "content": "X",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "62": {
500
+ "content": "Y",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "63": {
508
+ "content": "Z",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "64": {
516
+ "content": "!",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "65": {
524
+ "content": "\"",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "66": {
532
+ "content": "#",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "67": {
540
+ "content": "$",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "68": {
548
+ "content": "%",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "69": {
556
+ "content": "&",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "70": {
564
+ "content": "'",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "71": {
572
+ "content": "(",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "72": {
580
+ "content": ")",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "73": {
588
+ "content": "*",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "74": {
596
+ "content": "+",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "75": {
604
+ "content": ",",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "76": {
612
+ "content": "-",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "77": {
620
+ "content": ".",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "78": {
628
+ "content": "/",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "79": {
636
+ "content": ":",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "80": {
644
+ "content": ";",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "81": {
652
+ "content": "<",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "82": {
660
+ "content": "=",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "83": {
668
+ "content": ">",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "84": {
676
+ "content": "?",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "85": {
684
+ "content": "@",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "86": {
692
+ "content": "[",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "87": {
700
+ "content": "\\",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "88": {
708
+ "content": "]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "89": {
716
+ "content": "^",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "90": {
724
+ "content": "_",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "91": {
732
+ "content": "`",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "92": {
740
+ "content": "{",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "93": {
748
+ "content": "|",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "94": {
756
+ "content": "}",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95": {
764
+ "content": "~",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "96": {
772
+ "content": " ",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "97": {
780
+ "content": "\t",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "98": {
788
+ "content": "\n",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "99": {
796
+ "content": "\r",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "100": {
804
+ "content": "\u000b",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "101": {
812
+ "content": "\f",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "102": {
820
+ "content": "ö",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "103": {
828
+ "content": "Ö",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "104": {
836
+ "content": "ä",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "105": {
844
+ "content": "Ä",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "106": {
852
+ "content": "ü",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "107": {
860
+ "content": "Ü",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "108": {
868
+ "content": "ß",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "109": {
876
+ "content": "ẞ",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ }
883
+ },
884
+ "bos_token": "<|endoftext|>",
885
+ "clean_up_tokenization_spaces": false,
886
+ "eos_token": "<|endoftext|>",
887
+ "model_max_length": 1000000000000000019884624838656,
888
+ "pad_token": "<|endoftext|>",
889
+ "tokenizer_class": "PreTrainedTokenizerFast"
890
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e1b3367f16fbd22220eaa614f1149444e2be098126c9c159b5ad8fe77be635
3
+ size 5368