fhdz commited on
Commit
6e380e1
·
verified ·
1 Parent(s): d18bce2

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. bpe.model +3 -0
  2. config.json +1119 -0
  3. model.00.safetensors +3 -0
  4. tokenizer.json +0 -0
  5. vocab.json +0 -0
  6. vocab.txt +0 -0
bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2d9a6d66c76b4af0aee66a975d078a685b53076724a09c4581bed7b15660f7
3
+ size 3243763
config.json ADDED
@@ -0,0 +1,1119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "data": null,
3
+ "tgt_vocab_size": 128256,
4
+ "transforms": [
5
+ "onmt_tokenize",
6
+ "filtertoolong"
7
+ ],
8
+ "src_vocab": null,
9
+ "decoder_start_token": "<s>",
10
+ "skip_empty_level": "silent",
11
+ "share_vocab": true,
12
+ "n_sample": 0,
13
+ "vocab_size_multiple": 8,
14
+ "save_data": null,
15
+ "tgt_vocab": null,
16
+ "src_vocab_size": 128256,
17
+ "training": {
18
+ "accum_count": [
19
+ 32
20
+ ],
21
+ "batch_size": 896,
22
+ "accum_steps": [
23
+ 0
24
+ ],
25
+ "group_size": 0,
26
+ "valid_batch_size": 256,
27
+ "batch_size_multiple": 1,
28
+ "normalization": "tokens",
29
+ "quant_type": "",
30
+ "w_bit": 0,
31
+ "compute_dtype": "torch.bfloat16",
32
+ "batch_type": "tokens",
33
+ "quant_layers": []
34
+ },
35
+ "transforms_configs": {
36
+ "filtertoolong": {
37
+ "tgt_seq_length": 512,
38
+ "src_seq_length": 512
39
+ },
40
+ "onmt_tokenize": {
41
+ "gpt2_pretok": true,
42
+ "src_subword_model": "${MODEL_PATH}/bpe.model",
43
+ "mapped_tokens": [
44
+ [
45
+ "<|begin_of_text|>",
46
+ "⦅begin_of_text⦆"
47
+ ],
48
+ [
49
+ "<|end_of_text|>",
50
+ "⦅end_of_text⦆"
51
+ ],
52
+ [
53
+ "<|reserved_special_token_0|>",
54
+ "⦅reserved_special_token_0⦆"
55
+ ],
56
+ [
57
+ "<|reserved_special_token_1|>",
58
+ "⦅reserved_special_token_1⦆"
59
+ ],
60
+ [
61
+ "<|reserved_special_token_2|>",
62
+ "⦅reserved_special_token_2⦆"
63
+ ],
64
+ [
65
+ "<|reserved_special_token_3|>",
66
+ "⦅reserved_special_token_3⦆"
67
+ ],
68
+ [
69
+ "<|start_header_id|>",
70
+ "⦅start_header_id⦆"
71
+ ],
72
+ [
73
+ "<|end_header_id|>",
74
+ "⦅end_header_id⦆"
75
+ ],
76
+ [
77
+ "<|reserved_special_token_4|>",
78
+ "⦅reserved_special_token_4⦆"
79
+ ],
80
+ [
81
+ "<|eot_id|>",
82
+ "⦅eot_id⦆"
83
+ ],
84
+ [
85
+ "<|reserved_special_token_5|>",
86
+ "⦅reserved_special_token_5⦆"
87
+ ],
88
+ [
89
+ "<|reserved_special_token_6|>",
90
+ "⦅reserved_special_token_6⦆"
91
+ ],
92
+ [
93
+ "<|reserved_special_token_7|>",
94
+ "⦅reserved_special_token_7⦆"
95
+ ],
96
+ [
97
+ "<|reserved_special_token_8|>",
98
+ "⦅reserved_special_token_8⦆"
99
+ ],
100
+ [
101
+ "<|reserved_special_token_9|>",
102
+ "⦅reserved_special_token_9⦆"
103
+ ],
104
+ [
105
+ "<|reserved_special_token_10|>",
106
+ "⦅reserved_special_token_10⦆"
107
+ ],
108
+ [
109
+ "<|reserved_special_token_11|>",
110
+ "⦅reserved_special_token_11⦆"
111
+ ],
112
+ [
113
+ "<|reserved_special_token_12|>",
114
+ "⦅reserved_special_token_12⦆"
115
+ ],
116
+ [
117
+ "<|reserved_special_token_13|>",
118
+ "⦅reserved_special_token_13⦆"
119
+ ],
120
+ [
121
+ "<|reserved_special_token_14|>",
122
+ "⦅reserved_special_token_14⦆"
123
+ ],
124
+ [
125
+ "<|reserved_special_token_15|>",
126
+ "⦅reserved_special_token_15⦆"
127
+ ],
128
+ [
129
+ "<|reserved_special_token_16|>",
130
+ "⦅reserved_special_token_16⦆"
131
+ ],
132
+ [
133
+ "<|reserved_special_token_17|>",
134
+ "⦅reserved_special_token_17⦆"
135
+ ],
136
+ [
137
+ "<|reserved_special_token_18|>",
138
+ "⦅reserved_special_token_18⦆"
139
+ ],
140
+ [
141
+ "<|reserved_special_token_19|>",
142
+ "⦅reserved_special_token_19⦆"
143
+ ],
144
+ [
145
+ "<|reserved_special_token_20|>",
146
+ "⦅reserved_special_token_20⦆"
147
+ ],
148
+ [
149
+ "<|reserved_special_token_21|>",
150
+ "⦅reserved_special_token_21⦆"
151
+ ],
152
+ [
153
+ "<|reserved_special_token_22|>",
154
+ "⦅reserved_special_token_22⦆"
155
+ ],
156
+ [
157
+ "<|reserved_special_token_23|>",
158
+ "⦅reserved_special_token_23⦆"
159
+ ],
160
+ [
161
+ "<|reserved_special_token_24|>",
162
+ "⦅reserved_special_token_24⦆"
163
+ ],
164
+ [
165
+ "<|reserved_special_token_25|>",
166
+ "⦅reserved_special_token_25⦆"
167
+ ],
168
+ [
169
+ "<|reserved_special_token_26|>",
170
+ "⦅reserved_special_token_26⦆"
171
+ ],
172
+ [
173
+ "<|reserved_special_token_27|>",
174
+ "⦅reserved_special_token_27⦆"
175
+ ],
176
+ [
177
+ "<|reserved_special_token_28|>",
178
+ "⦅reserved_special_token_28⦆"
179
+ ],
180
+ [
181
+ "<|reserved_special_token_29|>",
182
+ "⦅reserved_special_token_29⦆"
183
+ ],
184
+ [
185
+ "<|reserved_special_token_30|>",
186
+ "⦅reserved_special_token_30⦆"
187
+ ],
188
+ [
189
+ "<|reserved_special_token_31|>",
190
+ "⦅reserved_special_token_31⦆"
191
+ ],
192
+ [
193
+ "<|reserved_special_token_32|>",
194
+ "⦅reserved_special_token_32⦆"
195
+ ],
196
+ [
197
+ "<|reserved_special_token_33|>",
198
+ "⦅reserved_special_token_33⦆"
199
+ ],
200
+ [
201
+ "<|reserved_special_token_34|>",
202
+ "⦅reserved_special_token_34⦆"
203
+ ],
204
+ [
205
+ "<|reserved_special_token_35|>",
206
+ "⦅reserved_special_token_35⦆"
207
+ ],
208
+ [
209
+ "<|reserved_special_token_36|>",
210
+ "⦅reserved_special_token_36⦆"
211
+ ],
212
+ [
213
+ "<|reserved_special_token_37|>",
214
+ "⦅reserved_special_token_37⦆"
215
+ ],
216
+ [
217
+ "<|reserved_special_token_38|>",
218
+ "⦅reserved_special_token_38⦆"
219
+ ],
220
+ [
221
+ "<|reserved_special_token_39|>",
222
+ "⦅reserved_special_token_39⦆"
223
+ ],
224
+ [
225
+ "<|reserved_special_token_40|>",
226
+ "⦅reserved_special_token_40⦆"
227
+ ],
228
+ [
229
+ "<|reserved_special_token_41|>",
230
+ "⦅reserved_special_token_41⦆"
231
+ ],
232
+ [
233
+ "<|reserved_special_token_42|>",
234
+ "⦅reserved_special_token_42⦆"
235
+ ],
236
+ [
237
+ "<|reserved_special_token_43|>",
238
+ "⦅reserved_special_token_43⦆"
239
+ ],
240
+ [
241
+ "<|reserved_special_token_44|>",
242
+ "⦅reserved_special_token_44⦆"
243
+ ],
244
+ [
245
+ "<|reserved_special_token_45|>",
246
+ "⦅reserved_special_token_45⦆"
247
+ ],
248
+ [
249
+ "<|reserved_special_token_46|>",
250
+ "⦅reserved_special_token_46⦆"
251
+ ],
252
+ [
253
+ "<|reserved_special_token_47|>",
254
+ "⦅reserved_special_token_47⦆"
255
+ ],
256
+ [
257
+ "<|reserved_special_token_48|>",
258
+ "⦅reserved_special_token_48⦆"
259
+ ],
260
+ [
261
+ "<|reserved_special_token_49|>",
262
+ "⦅reserved_special_token_49⦆"
263
+ ],
264
+ [
265
+ "<|reserved_special_token_50|>",
266
+ "⦅reserved_special_token_50⦆"
267
+ ],
268
+ [
269
+ "<|reserved_special_token_51|>",
270
+ "⦅reserved_special_token_51⦆"
271
+ ],
272
+ [
273
+ "<|reserved_special_token_52|>",
274
+ "⦅reserved_special_token_52⦆"
275
+ ],
276
+ [
277
+ "<|reserved_special_token_53|>",
278
+ "⦅reserved_special_token_53⦆"
279
+ ],
280
+ [
281
+ "<|reserved_special_token_54|>",
282
+ "⦅reserved_special_token_54⦆"
283
+ ],
284
+ [
285
+ "<|reserved_special_token_55|>",
286
+ "⦅reserved_special_token_55⦆"
287
+ ],
288
+ [
289
+ "<|reserved_special_token_56|>",
290
+ "⦅reserved_special_token_56⦆"
291
+ ],
292
+ [
293
+ "<|reserved_special_token_57|>",
294
+ "⦅reserved_special_token_57⦆"
295
+ ],
296
+ [
297
+ "<|reserved_special_token_58|>",
298
+ "⦅reserved_special_token_58⦆"
299
+ ],
300
+ [
301
+ "<|reserved_special_token_59|>",
302
+ "⦅reserved_special_token_59⦆"
303
+ ],
304
+ [
305
+ "<|reserved_special_token_60|>",
306
+ "⦅reserved_special_token_60⦆"
307
+ ],
308
+ [
309
+ "<|reserved_special_token_61|>",
310
+ "⦅reserved_special_token_61⦆"
311
+ ],
312
+ [
313
+ "<|reserved_special_token_62|>",
314
+ "⦅reserved_special_token_62⦆"
315
+ ],
316
+ [
317
+ "<|reserved_special_token_63|>",
318
+ "⦅reserved_special_token_63⦆"
319
+ ],
320
+ [
321
+ "<|reserved_special_token_64|>",
322
+ "⦅reserved_special_token_64⦆"
323
+ ],
324
+ [
325
+ "<|reserved_special_token_65|>",
326
+ "⦅reserved_special_token_65⦆"
327
+ ],
328
+ [
329
+ "<|reserved_special_token_66|>",
330
+ "⦅reserved_special_token_66⦆"
331
+ ],
332
+ [
333
+ "<|reserved_special_token_67|>",
334
+ "⦅reserved_special_token_67⦆"
335
+ ],
336
+ [
337
+ "<|reserved_special_token_68|>",
338
+ "⦅reserved_special_token_68⦆"
339
+ ],
340
+ [
341
+ "<|reserved_special_token_69|>",
342
+ "⦅reserved_special_token_69⦆"
343
+ ],
344
+ [
345
+ "<|reserved_special_token_70|>",
346
+ "⦅reserved_special_token_70⦆"
347
+ ],
348
+ [
349
+ "<|reserved_special_token_71|>",
350
+ "⦅reserved_special_token_71⦆"
351
+ ],
352
+ [
353
+ "<|reserved_special_token_72|>",
354
+ "⦅reserved_special_token_72⦆"
355
+ ],
356
+ [
357
+ "<|reserved_special_token_73|>",
358
+ "⦅reserved_special_token_73⦆"
359
+ ],
360
+ [
361
+ "<|reserved_special_token_74|>",
362
+ "⦅reserved_special_token_74⦆"
363
+ ],
364
+ [
365
+ "<|reserved_special_token_75|>",
366
+ "⦅reserved_special_token_75⦆"
367
+ ],
368
+ [
369
+ "<|reserved_special_token_76|>",
370
+ "⦅reserved_special_token_76⦆"
371
+ ],
372
+ [
373
+ "<|reserved_special_token_77|>",
374
+ "⦅reserved_special_token_77⦆"
375
+ ],
376
+ [
377
+ "<|reserved_special_token_78|>",
378
+ "⦅reserved_special_token_78⦆"
379
+ ],
380
+ [
381
+ "<|reserved_special_token_79|>",
382
+ "⦅reserved_special_token_79⦆"
383
+ ],
384
+ [
385
+ "<|reserved_special_token_80|>",
386
+ "⦅reserved_special_token_80⦆"
387
+ ],
388
+ [
389
+ "<|reserved_special_token_81|>",
390
+ "⦅reserved_special_token_81⦆"
391
+ ],
392
+ [
393
+ "<|reserved_special_token_82|>",
394
+ "⦅reserved_special_token_82⦆"
395
+ ],
396
+ [
397
+ "<|reserved_special_token_83|>",
398
+ "⦅reserved_special_token_83⦆"
399
+ ],
400
+ [
401
+ "<|reserved_special_token_84|>",
402
+ "⦅reserved_special_token_84⦆"
403
+ ],
404
+ [
405
+ "<|reserved_special_token_85|>",
406
+ "⦅reserved_special_token_85⦆"
407
+ ],
408
+ [
409
+ "<|reserved_special_token_86|>",
410
+ "⦅reserved_special_token_86⦆"
411
+ ],
412
+ [
413
+ "<|reserved_special_token_87|>",
414
+ "⦅reserved_special_token_87⦆"
415
+ ],
416
+ [
417
+ "<|reserved_special_token_88|>",
418
+ "⦅reserved_special_token_88⦆"
419
+ ],
420
+ [
421
+ "<|reserved_special_token_89|>",
422
+ "⦅reserved_special_token_89⦆"
423
+ ],
424
+ [
425
+ "<|reserved_special_token_90|>",
426
+ "⦅reserved_special_token_90⦆"
427
+ ],
428
+ [
429
+ "<|reserved_special_token_91|>",
430
+ "⦅reserved_special_token_91⦆"
431
+ ],
432
+ [
433
+ "<|reserved_special_token_92|>",
434
+ "⦅reserved_special_token_92⦆"
435
+ ],
436
+ [
437
+ "<|reserved_special_token_93|>",
438
+ "⦅reserved_special_token_93⦆"
439
+ ],
440
+ [
441
+ "<|reserved_special_token_94|>",
442
+ "⦅reserved_special_token_94⦆"
443
+ ],
444
+ [
445
+ "<|reserved_special_token_95|>",
446
+ "⦅reserved_special_token_95⦆"
447
+ ],
448
+ [
449
+ "<|reserved_special_token_96|>",
450
+ "⦅reserved_special_token_96⦆"
451
+ ],
452
+ [
453
+ "<|reserved_special_token_97|>",
454
+ "⦅reserved_special_token_97⦆"
455
+ ],
456
+ [
457
+ "<|reserved_special_token_98|>",
458
+ "⦅reserved_special_token_98⦆"
459
+ ],
460
+ [
461
+ "<|reserved_special_token_99|>",
462
+ "⦅reserved_special_token_99⦆"
463
+ ],
464
+ [
465
+ "<|reserved_special_token_100|>",
466
+ "⦅reserved_special_token_100⦆"
467
+ ],
468
+ [
469
+ "<|reserved_special_token_101|>",
470
+ "⦅reserved_special_token_101⦆"
471
+ ],
472
+ [
473
+ "<|reserved_special_token_102|>",
474
+ "⦅reserved_special_token_102⦆"
475
+ ],
476
+ [
477
+ "<|reserved_special_token_103|>",
478
+ "⦅reserved_special_token_103⦆"
479
+ ],
480
+ [
481
+ "<|reserved_special_token_104|>",
482
+ "⦅reserved_special_token_104⦆"
483
+ ],
484
+ [
485
+ "<|reserved_special_token_105|>",
486
+ "⦅reserved_special_token_105⦆"
487
+ ],
488
+ [
489
+ "<|reserved_special_token_106|>",
490
+ "⦅reserved_special_token_106⦆"
491
+ ],
492
+ [
493
+ "<|reserved_special_token_107|>",
494
+ "⦅reserved_special_token_107⦆"
495
+ ],
496
+ [
497
+ "<|reserved_special_token_108|>",
498
+ "⦅reserved_special_token_108⦆"
499
+ ],
500
+ [
501
+ "<|reserved_special_token_109|>",
502
+ "⦅reserved_special_token_109⦆"
503
+ ],
504
+ [
505
+ "<|reserved_special_token_110|>",
506
+ "⦅reserved_special_token_110⦆"
507
+ ],
508
+ [
509
+ "<|reserved_special_token_111|>",
510
+ "⦅reserved_special_token_111⦆"
511
+ ],
512
+ [
513
+ "<|reserved_special_token_112|>",
514
+ "⦅reserved_special_token_112⦆"
515
+ ],
516
+ [
517
+ "<|reserved_special_token_113|>",
518
+ "⦅reserved_special_token_113⦆"
519
+ ],
520
+ [
521
+ "<|reserved_special_token_114|>",
522
+ "⦅reserved_special_token_114⦆"
523
+ ],
524
+ [
525
+ "<|reserved_special_token_115|>",
526
+ "⦅reserved_special_token_115⦆"
527
+ ],
528
+ [
529
+ "<|reserved_special_token_116|>",
530
+ "⦅reserved_special_token_116⦆"
531
+ ],
532
+ [
533
+ "<|reserved_special_token_117|>",
534
+ "⦅reserved_special_token_117⦆"
535
+ ],
536
+ [
537
+ "<|reserved_special_token_118|>",
538
+ "⦅reserved_special_token_118⦆"
539
+ ],
540
+ [
541
+ "<|reserved_special_token_119|>",
542
+ "⦅reserved_special_token_119⦆"
543
+ ],
544
+ [
545
+ "<|reserved_special_token_120|>",
546
+ "⦅reserved_special_token_120⦆"
547
+ ],
548
+ [
549
+ "<|reserved_special_token_121|>",
550
+ "⦅reserved_special_token_121⦆"
551
+ ],
552
+ [
553
+ "<|reserved_special_token_122|>",
554
+ "⦅reserved_special_token_122⦆"
555
+ ],
556
+ [
557
+ "<|reserved_special_token_123|>",
558
+ "⦅reserved_special_token_123⦆"
559
+ ],
560
+ [
561
+ "<|reserved_special_token_124|>",
562
+ "⦅reserved_special_token_124⦆"
563
+ ],
564
+ [
565
+ "<|reserved_special_token_125|>",
566
+ "⦅reserved_special_token_125⦆"
567
+ ],
568
+ [
569
+ "<|reserved_special_token_126|>",
570
+ "⦅reserved_special_token_126⦆"
571
+ ],
572
+ [
573
+ "<|reserved_special_token_127|>",
574
+ "⦅reserved_special_token_127⦆"
575
+ ],
576
+ [
577
+ "<|reserved_special_token_128|>",
578
+ "⦅reserved_special_token_128⦆"
579
+ ],
580
+ [
581
+ "<|reserved_special_token_129|>",
582
+ "⦅reserved_special_token_129⦆"
583
+ ],
584
+ [
585
+ "<|reserved_special_token_130|>",
586
+ "⦅reserved_special_token_130⦆"
587
+ ],
588
+ [
589
+ "<|reserved_special_token_131|>",
590
+ "⦅reserved_special_token_131⦆"
591
+ ],
592
+ [
593
+ "<|reserved_special_token_132|>",
594
+ "⦅reserved_special_token_132⦆"
595
+ ],
596
+ [
597
+ "<|reserved_special_token_133|>",
598
+ "⦅reserved_special_token_133⦆"
599
+ ],
600
+ [
601
+ "<|reserved_special_token_134|>",
602
+ "⦅reserved_special_token_134⦆"
603
+ ],
604
+ [
605
+ "<|reserved_special_token_135|>",
606
+ "⦅reserved_special_token_135⦆"
607
+ ],
608
+ [
609
+ "<|reserved_special_token_136|>",
610
+ "⦅reserved_special_token_136⦆"
611
+ ],
612
+ [
613
+ "<|reserved_special_token_137|>",
614
+ "⦅reserved_special_token_137⦆"
615
+ ],
616
+ [
617
+ "<|reserved_special_token_138|>",
618
+ "⦅reserved_special_token_138⦆"
619
+ ],
620
+ [
621
+ "<|reserved_special_token_139|>",
622
+ "⦅reserved_special_token_139⦆"
623
+ ],
624
+ [
625
+ "<|reserved_special_token_140|>",
626
+ "⦅reserved_special_token_140⦆"
627
+ ],
628
+ [
629
+ "<|reserved_special_token_141|>",
630
+ "⦅reserved_special_token_141⦆"
631
+ ],
632
+ [
633
+ "<|reserved_special_token_142|>",
634
+ "⦅reserved_special_token_142⦆"
635
+ ],
636
+ [
637
+ "<|reserved_special_token_143|>",
638
+ "⦅reserved_special_token_143⦆"
639
+ ],
640
+ [
641
+ "<|reserved_special_token_144|>",
642
+ "⦅reserved_special_token_144⦆"
643
+ ],
644
+ [
645
+ "<|reserved_special_token_145|>",
646
+ "⦅reserved_special_token_145⦆"
647
+ ],
648
+ [
649
+ "<|reserved_special_token_146|>",
650
+ "⦅reserved_special_token_146⦆"
651
+ ],
652
+ [
653
+ "<|reserved_special_token_147|>",
654
+ "⦅reserved_special_token_147⦆"
655
+ ],
656
+ [
657
+ "<|reserved_special_token_148|>",
658
+ "⦅reserved_special_token_148⦆"
659
+ ],
660
+ [
661
+ "<|reserved_special_token_149|>",
662
+ "⦅reserved_special_token_149⦆"
663
+ ],
664
+ [
665
+ "<|reserved_special_token_150|>",
666
+ "⦅reserved_special_token_150⦆"
667
+ ],
668
+ [
669
+ "<|reserved_special_token_151|>",
670
+ "⦅reserved_special_token_151⦆"
671
+ ],
672
+ [
673
+ "<|reserved_special_token_152|>",
674
+ "⦅reserved_special_token_152⦆"
675
+ ],
676
+ [
677
+ "<|reserved_special_token_153|>",
678
+ "⦅reserved_special_token_153⦆"
679
+ ],
680
+ [
681
+ "<|reserved_special_token_154|>",
682
+ "⦅reserved_special_token_154⦆"
683
+ ],
684
+ [
685
+ "<|reserved_special_token_155|>",
686
+ "⦅reserved_special_token_155⦆"
687
+ ],
688
+ [
689
+ "<|reserved_special_token_156|>",
690
+ "⦅reserved_special_token_156⦆"
691
+ ],
692
+ [
693
+ "<|reserved_special_token_157|>",
694
+ "⦅reserved_special_token_157⦆"
695
+ ],
696
+ [
697
+ "<|reserved_special_token_158|>",
698
+ "⦅reserved_special_token_158⦆"
699
+ ],
700
+ [
701
+ "<|reserved_special_token_159|>",
702
+ "⦅reserved_special_token_159⦆"
703
+ ],
704
+ [
705
+ "<|reserved_special_token_160|>",
706
+ "⦅reserved_special_token_160⦆"
707
+ ],
708
+ [
709
+ "<|reserved_special_token_161|>",
710
+ "⦅reserved_special_token_161⦆"
711
+ ],
712
+ [
713
+ "<|reserved_special_token_162|>",
714
+ "⦅reserved_special_token_162⦆"
715
+ ],
716
+ [
717
+ "<|reserved_special_token_163|>",
718
+ "⦅reserved_special_token_163⦆"
719
+ ],
720
+ [
721
+ "<|reserved_special_token_164|>",
722
+ "⦅reserved_special_token_164⦆"
723
+ ],
724
+ [
725
+ "<|reserved_special_token_165|>",
726
+ "⦅reserved_special_token_165⦆"
727
+ ],
728
+ [
729
+ "<|reserved_special_token_166|>",
730
+ "⦅reserved_special_token_166⦆"
731
+ ],
732
+ [
733
+ "<|reserved_special_token_167|>",
734
+ "⦅reserved_special_token_167⦆"
735
+ ],
736
+ [
737
+ "<|reserved_special_token_168|>",
738
+ "⦅reserved_special_token_168⦆"
739
+ ],
740
+ [
741
+ "<|reserved_special_token_169|>",
742
+ "⦅reserved_special_token_169⦆"
743
+ ],
744
+ [
745
+ "<|reserved_special_token_170|>",
746
+ "⦅reserved_special_token_170⦆"
747
+ ],
748
+ [
749
+ "<|reserved_special_token_171|>",
750
+ "⦅reserved_special_token_171⦆"
751
+ ],
752
+ [
753
+ "<|reserved_special_token_172|>",
754
+ "⦅reserved_special_token_172⦆"
755
+ ],
756
+ [
757
+ "<|reserved_special_token_173|>",
758
+ "⦅reserved_special_token_173⦆"
759
+ ],
760
+ [
761
+ "<|reserved_special_token_174|>",
762
+ "⦅reserved_special_token_174⦆"
763
+ ],
764
+ [
765
+ "<|reserved_special_token_175|>",
766
+ "⦅reserved_special_token_175⦆"
767
+ ],
768
+ [
769
+ "<|reserved_special_token_176|>",
770
+ "⦅reserved_special_token_176⦆"
771
+ ],
772
+ [
773
+ "<|reserved_special_token_177|>",
774
+ "⦅reserved_special_token_177⦆"
775
+ ],
776
+ [
777
+ "<|reserved_special_token_178|>",
778
+ "⦅reserved_special_token_178⦆"
779
+ ],
780
+ [
781
+ "<|reserved_special_token_179|>",
782
+ "⦅reserved_special_token_179⦆"
783
+ ],
784
+ [
785
+ "<|reserved_special_token_180|>",
786
+ "⦅reserved_special_token_180⦆"
787
+ ],
788
+ [
789
+ "<|reserved_special_token_181|>",
790
+ "⦅reserved_special_token_181⦆"
791
+ ],
792
+ [
793
+ "<|reserved_special_token_182|>",
794
+ "⦅reserved_special_token_182⦆"
795
+ ],
796
+ [
797
+ "<|reserved_special_token_183|>",
798
+ "⦅reserved_special_token_183⦆"
799
+ ],
800
+ [
801
+ "<|reserved_special_token_184|>",
802
+ "⦅reserved_special_token_184⦆"
803
+ ],
804
+ [
805
+ "<|reserved_special_token_185|>",
806
+ "⦅reserved_special_token_185⦆"
807
+ ],
808
+ [
809
+ "<|reserved_special_token_186|>",
810
+ "⦅reserved_special_token_186⦆"
811
+ ],
812
+ [
813
+ "<|reserved_special_token_187|>",
814
+ "⦅reserved_special_token_187⦆"
815
+ ],
816
+ [
817
+ "<|reserved_special_token_188|>",
818
+ "⦅reserved_special_token_188⦆"
819
+ ],
820
+ [
821
+ "<|reserved_special_token_189|>",
822
+ "⦅reserved_special_token_189⦆"
823
+ ],
824
+ [
825
+ "<|reserved_special_token_190|>",
826
+ "⦅reserved_special_token_190⦆"
827
+ ],
828
+ [
829
+ "<|reserved_special_token_191|>",
830
+ "⦅reserved_special_token_191⦆"
831
+ ],
832
+ [
833
+ "<|reserved_special_token_192|>",
834
+ "⦅reserved_special_token_192⦆"
835
+ ],
836
+ [
837
+ "<|reserved_special_token_193|>",
838
+ "⦅reserved_special_token_193⦆"
839
+ ],
840
+ [
841
+ "<|reserved_special_token_194|>",
842
+ "⦅reserved_special_token_194⦆"
843
+ ],
844
+ [
845
+ "<|reserved_special_token_195|>",
846
+ "⦅reserved_special_token_195⦆"
847
+ ],
848
+ [
849
+ "<|reserved_special_token_196|>",
850
+ "⦅reserved_special_token_196⦆"
851
+ ],
852
+ [
853
+ "<|reserved_special_token_197|>",
854
+ "⦅reserved_special_token_197⦆"
855
+ ],
856
+ [
857
+ "<|reserved_special_token_198|>",
858
+ "⦅reserved_special_token_198⦆"
859
+ ],
860
+ [
861
+ "<|reserved_special_token_199|>",
862
+ "⦅reserved_special_token_199⦆"
863
+ ],
864
+ [
865
+ "<|reserved_special_token_200|>",
866
+ "⦅reserved_special_token_200⦆"
867
+ ],
868
+ [
869
+ "<|reserved_special_token_201|>",
870
+ "⦅reserved_special_token_201⦆"
871
+ ],
872
+ [
873
+ "<|reserved_special_token_202|>",
874
+ "⦅reserved_special_token_202⦆"
875
+ ],
876
+ [
877
+ "<|reserved_special_token_203|>",
878
+ "⦅reserved_special_token_203⦆"
879
+ ],
880
+ [
881
+ "<|reserved_special_token_204|>",
882
+ "⦅reserved_special_token_204⦆"
883
+ ],
884
+ [
885
+ "<|reserved_special_token_205|>",
886
+ "⦅reserved_special_token_205⦆"
887
+ ],
888
+ [
889
+ "<|reserved_special_token_206|>",
890
+ "⦅reserved_special_token_206⦆"
891
+ ],
892
+ [
893
+ "<|reserved_special_token_207|>",
894
+ "⦅reserved_special_token_207⦆"
895
+ ],
896
+ [
897
+ "<|reserved_special_token_208|>",
898
+ "⦅reserved_special_token_208⦆"
899
+ ],
900
+ [
901
+ "<|reserved_special_token_209|>",
902
+ "⦅reserved_special_token_209⦆"
903
+ ],
904
+ [
905
+ "<|reserved_special_token_210|>",
906
+ "⦅reserved_special_token_210⦆"
907
+ ],
908
+ [
909
+ "<|reserved_special_token_211|>",
910
+ "⦅reserved_special_token_211⦆"
911
+ ],
912
+ [
913
+ "<|reserved_special_token_212|>",
914
+ "⦅reserved_special_token_212⦆"
915
+ ],
916
+ [
917
+ "<|reserved_special_token_213|>",
918
+ "⦅reserved_special_token_213⦆"
919
+ ],
920
+ [
921
+ "<|reserved_special_token_214|>",
922
+ "⦅reserved_special_token_214⦆"
923
+ ],
924
+ [
925
+ "<|reserved_special_token_215|>",
926
+ "⦅reserved_special_token_215⦆"
927
+ ],
928
+ [
929
+ "<|reserved_special_token_216|>",
930
+ "⦅reserved_special_token_216⦆"
931
+ ],
932
+ [
933
+ "<|reserved_special_token_217|>",
934
+ "⦅reserved_special_token_217⦆"
935
+ ],
936
+ [
937
+ "<|reserved_special_token_218|>",
938
+ "⦅reserved_special_token_218⦆"
939
+ ],
940
+ [
941
+ "<|reserved_special_token_219|>",
942
+ "⦅reserved_special_token_219⦆"
943
+ ],
944
+ [
945
+ "<|reserved_special_token_220|>",
946
+ "⦅reserved_special_token_220⦆"
947
+ ],
948
+ [
949
+ "<|reserved_special_token_221|>",
950
+ "⦅reserved_special_token_221⦆"
951
+ ],
952
+ [
953
+ "<|reserved_special_token_222|>",
954
+ "⦅reserved_special_token_222⦆"
955
+ ],
956
+ [
957
+ "<|reserved_special_token_223|>",
958
+ "⦅reserved_special_token_223⦆"
959
+ ],
960
+ [
961
+ "<|reserved_special_token_224|>",
962
+ "⦅reserved_special_token_224⦆"
963
+ ],
964
+ [
965
+ "<|reserved_special_token_225|>",
966
+ "⦅reserved_special_token_225⦆"
967
+ ],
968
+ [
969
+ "<|reserved_special_token_226|>",
970
+ "⦅reserved_special_token_226⦆"
971
+ ],
972
+ [
973
+ "<|reserved_special_token_227|>",
974
+ "⦅reserved_special_token_227⦆"
975
+ ],
976
+ [
977
+ "<|reserved_special_token_228|>",
978
+ "⦅reserved_special_token_228⦆"
979
+ ],
980
+ [
981
+ "<|reserved_special_token_229|>",
982
+ "⦅reserved_special_token_229⦆"
983
+ ],
984
+ [
985
+ "<|reserved_special_token_230|>",
986
+ "⦅reserved_special_token_230⦆"
987
+ ],
988
+ [
989
+ "<|reserved_special_token_231|>",
990
+ "⦅reserved_special_token_231⦆"
991
+ ],
992
+ [
993
+ "<|reserved_special_token_232|>",
994
+ "⦅reserved_special_token_232⦆"
995
+ ],
996
+ [
997
+ "<|reserved_special_token_233|>",
998
+ "⦅reserved_special_token_233⦆"
999
+ ],
1000
+ [
1001
+ "<|reserved_special_token_234|>",
1002
+ "⦅reserved_special_token_234⦆"
1003
+ ],
1004
+ [
1005
+ "<|reserved_special_token_235|>",
1006
+ "⦅reserved_special_token_235⦆"
1007
+ ],
1008
+ [
1009
+ "<|reserved_special_token_236|>",
1010
+ "⦅reserved_special_token_236⦆"
1011
+ ],
1012
+ [
1013
+ "<|reserved_special_token_237|>",
1014
+ "⦅reserved_special_token_237⦆"
1015
+ ],
1016
+ [
1017
+ "<|reserved_special_token_238|>",
1018
+ "⦅reserved_special_token_238⦆"
1019
+ ],
1020
+ [
1021
+ "<|reserved_special_token_239|>",
1022
+ "⦅reserved_special_token_239⦆"
1023
+ ],
1024
+ [
1025
+ "<|reserved_special_token_240|>",
1026
+ "⦅reserved_special_token_240⦆"
1027
+ ],
1028
+ [
1029
+ "<|reserved_special_token_241|>",
1030
+ "⦅reserved_special_token_241⦆"
1031
+ ],
1032
+ [
1033
+ "<|reserved_special_token_242|>",
1034
+ "⦅reserved_special_token_242⦆"
1035
+ ],
1036
+ [
1037
+ "<|reserved_special_token_243|>",
1038
+ "⦅reserved_special_token_243⦆"
1039
+ ],
1040
+ [
1041
+ "<|reserved_special_token_244|>",
1042
+ "⦅reserved_special_token_244⦆"
1043
+ ],
1044
+ [
1045
+ "<|reserved_special_token_245|>",
1046
+ "⦅reserved_special_token_245⦆"
1047
+ ],
1048
+ [
1049
+ "<|reserved_special_token_246|>",
1050
+ "⦅reserved_special_token_246⦆"
1051
+ ],
1052
+ [
1053
+ "<|reserved_special_token_247|>",
1054
+ "⦅reserved_special_token_247⦆"
1055
+ ],
1056
+ [
1057
+ "<|reserved_special_token_248|>",
1058
+ "⦅reserved_special_token_248⦆"
1059
+ ],
1060
+ [
1061
+ "<|reserved_special_token_249|>",
1062
+ "⦅reserved_special_token_249⦆"
1063
+ ],
1064
+ [
1065
+ "<|reserved_special_token_250|>",
1066
+ "⦅reserved_special_token_250⦆"
1067
+ ]
1068
+ ],
1069
+ "src_subword_type": "bpe"
1070
+ }
1071
+ },
1072
+ "model": {
1073
+ "num_experts_per_tok": 0,
1074
+ "add_ffnbias": false,
1075
+ "left_pad": true,
1076
+ "layer_norm": "rms",
1077
+ "num_experts": 0,
1078
+ "heads": 32,
1079
+ "parallel_residual": false,
1080
+ "add_qkvbias": false,
1081
+ "head_dim": null,
1082
+ "transformer_ff": 14336,
1083
+ "heads_kv": 8,
1084
+ "norm_eps": 1e-05,
1085
+ "architecture": "transformer_lm",
1086
+ "mlp_activation_fn": "gated-silu",
1087
+ "hidden_size": 4096,
1088
+ "shared_layer_norm": false,
1089
+ "sliding_window": 0,
1090
+ "layers": 32,
1091
+ "embeddings": {
1092
+ "n_positions": 0,
1093
+ "position_encoding_type": "Rotary",
1094
+ "src_word_vec_size": 4096,
1095
+ "tgt_word_vec_size": 4096
1096
+ },
1097
+ "rope_config": {
1098
+ "rotary_theta": 500000,
1099
+ "rotary_interleave": false
1100
+ },
1101
+ "decoder": {
1102
+ "position_encoding_type": "Rotary",
1103
+ "decoder_type": "transformer_lm",
1104
+ "n_positions": 0,
1105
+ "tgt_word_vec_size": 4096,
1106
+ "rope_config": {
1107
+ "rotary_theta": 500000,
1108
+ "rotary_interleave": false
1109
+ }
1110
+ }
1111
+ },
1112
+ "inference": {
1113
+ "optional_eos": [],
1114
+ "top_p": 0.9,
1115
+ "temperature": 0.6,
1116
+ "max_length": 4096,
1117
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}"
1118
+ }
1119
+ }
model.00.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:647f8f56c9608fdddbfdd9347762f2e03377f7a792a1e2a06a196fea5266fb1a
3
+ size 16060817952
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.txt ADDED
The diff for this file is too large to render. See raw diff