Hugging Face's logo

Crossberry
/
evols

Safetensors
llama
Model card Files
xet
 Community
Crossberry commited on
Commit
29fa93b
·
verified ·
1 Parent(s): 28e136f

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. tokenizer.json +574 -0
  4. tokenizer_config.json +10 -0
  5. training_args.bin +3 -0
config.json CHANGED
@@ -27,6 +27,6 @@
27
  },
28
  "tie_word_embeddings": false,
29
  "transformers_version": "5.8.0",
30
- "use_cache": true,
31
  "vocab_size": 32000
32
  }
 
27
  },
28
  "tie_word_embeddings": false,
29
  "transformers_version": "5.8.0",
30
+ "use_cache": false,
31
  "vocab_size": 32000
32
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb5acefc9faa4b4c9b82dc6280bb36900ceaef21ae97a1947b37c46967d900b5
3
  size 76035200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c4d7330812b3f35175b037c71fcf3c311c95dc3c0a4c3e8c181bd755d8d392
3
  size 76035200
tokenizer.json ADDED
@@ -0,0 +1,574 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
11
+ "Fixed": 128
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 1,
16
+ "pad_type_id": 0,
17
+ "pad_token": "<pad>"
18
+ },
19
+ "added_tokens": [
20
+ {
21
+ "id": 0,
22
+ "content": "<s>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 1,
31
+ "content": "<pad>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 2,
40
+ "content": "</s>",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": false,
45
+ "special": true
46
+ },
47
+ {
48
+ "id": 3,
49
+ "content": "<unk>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 4,
58
+ "content": "<mask>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ {
66
+ "id": 302,
67
+ "content": "<mask",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ }
74
+ ],
75
+ "normalizer": null,
76
+ "pre_tokenizer": {
77
+ "type": "ByteLevel",
78
+ "add_prefix_space": false,
79
+ "trim_offsets": true,
80
+ "use_regex": true
81
+ },
82
+ "post_processor": {
83
+ "type": "ByteLevel",
84
+ "add_prefix_space": true,
85
+ "trim_offsets": false,
86
+ "use_regex": true
87
+ },
88
+ "decoder": {
89
+ "type": "ByteLevel",
90
+ "add_prefix_space": true,
91
+ "trim_offsets": true,
92
+ "use_regex": true
93
+ },
94
+ "model": {
95
+ "type": "BPE",
96
+ "dropout": null,
97
+ "unk_token": null,
98
+ "continuing_subword_prefix": null,
99
+ "end_of_word_suffix": null,
100
+ "fuse_unk": false,
101
+ "byte_fallback": false,
102
+ "ignore_merges": false,
103
+ "vocab": {
104
+ "<s>": 0,
105
+ "<pad>": 1,
106
+ "</s>": 2,
107
+ "<unk>": 3,
108
+ "<mask>": 4,
109
+ "!": 5,
110
+ "\"": 6,
111
+ "#": 7,
112
+ "$": 8,
113
+ "%": 9,
114
+ "&": 10,
115
+ "'": 11,
116
+ "(": 12,
117
+ ")": 13,
118
+ "*": 14,
119
+ "+": 15,
120
+ ",": 16,
121
+ "-": 17,
122
+ ".": 18,
123
+ "/": 19,
124
+ "0": 20,
125
+ "1": 21,
126
+ "2": 22,
127
+ "3": 23,
128
+ "4": 24,
129
+ "5": 25,
130
+ "6": 26,
131
+ "7": 27,
132
+ "8": 28,
133
+ "9": 29,
134
+ ":": 30,
135
+ ";": 31,
136
+ "<": 32,
137
+ "=": 33,
138
+ ">": 34,
139
+ "?": 35,
140
+ "@": 36,
141
+ "A": 37,
142
+ "B": 38,
143
+ "C": 39,
144
+ "D": 40,
145
+ "E": 41,
146
+ "F": 42,
147
+ "G": 43,
148
+ "H": 44,
149
+ "I": 45,
150
+ "J": 46,
151
+ "K": 47,
152
+ "L": 48,
153
+ "M": 49,
154
+ "N": 50,
155
+ "O": 51,
156
+ "P": 52,
157
+ "Q": 53,
158
+ "R": 54,
159
+ "S": 55,
160
+ "T": 56,
161
+ "U": 57,
162
+ "V": 58,
163
+ "W": 59,
164
+ "X": 60,
165
+ "Y": 61,
166
+ "Z": 62,
167
+ "[": 63,
168
+ "\\": 64,
169
+ "]": 65,
170
+ "^": 66,
171
+ "_": 67,
172
+ "`": 68,
173
+ "a": 69,
174
+ "b": 70,
175
+ "c": 71,
176
+ "d": 72,
177
+ "e": 73,
178
+ "f": 74,
179
+ "g": 75,
180
+ "h": 76,
181
+ "i": 77,
182
+ "j": 78,
183
+ "k": 79,
184
+ "l": 80,
185
+ "m": 81,
186
+ "n": 82,
187
+ "o": 83,
188
+ "p": 84,
189
+ "q": 85,
190
+ "r": 86,
191
+ "s": 87,
192
+ "t": 88,
193
+ "u": 89,
194
+ "v": 90,
195
+ "w": 91,
196
+ "x": 92,
197
+ "y": 93,
198
+ "z": 94,
199
+ "{": 95,
200
+ "|": 96,
201
+ "}": 97,
202
+ "~": 98,
203
+ "¡": 99,
204
+ "¢": 100,
205
+ "£": 101,
206
+ "¤": 102,
207
+ "¥": 103,
208
+ "¦": 104,
209
+ "§": 105,
210
+ "¨": 106,
211
+ "©": 107,
212
+ "ª": 108,
213
+ "«": 109,
214
+ "¬": 110,
215
+ "®": 111,
216
+ "¯": 112,
217
+ "°": 113,
218
+ "±": 114,
219
+ "²": 115,
220
+ "³": 116,
221
+ "´": 117,
222
+ "µ": 118,
223
+ "¶": 119,
224
+ "·": 120,
225
+ "¸": 121,
226
+ "¹": 122,
227
+ "º": 123,
228
+ "»": 124,
229
+ "¼": 125,
230
+ "½": 126,
231
+ "¾": 127,
232
+ "¿": 128,
233
+ "À": 129,
234
+ "Á": 130,
235
+ "Â": 131,
236
+ "Ã": 132,
237
+ "Ä": 133,
238
+ "Å": 134,
239
+ "Æ": 135,
240
+ "Ç": 136,
241
+ "È": 137,
242
+ "É": 138,
243
+ "Ê": 139,
244
+ "Ë": 140,
245
+ "Ì": 141,
246
+ "Í": 142,
247
+ "Î": 143,
248
+ "Ï": 144,
249
+ "Ð": 145,
250
+ "Ñ": 146,
251
+ "Ò": 147,
252
+ "Ó": 148,
253
+ "Ô": 149,
254
+ "Õ": 150,
255
+ "Ö": 151,
256
+ "×": 152,
257
+ "Ø": 153,
258
+ "Ù": 154,
259
+ "Ú": 155,
260
+ "Û": 156,
261
+ "Ü": 157,
262
+ "Ý": 158,
263
+ "Þ": 159,
264
+ "ß": 160,
265
+ "à": 161,
266
+ "á": 162,
267
+ "â": 163,
268
+ "ã": 164,
269
+ "ä": 165,
270
+ "å": 166,
271
+ "æ": 167,
272
+ "ç": 168,
273
+ "è": 169,
274
+ "é": 170,
275
+ "ê": 171,
276
+ "ë": 172,
277
+ "ì": 173,
278
+ "í": 174,
279
+ "î": 175,
280
+ "ï": 176,
281
+ "ð": 177,
282
+ "ñ": 178,
283
+ "ò": 179,
284
+ "ó": 180,
285
+ "ô": 181,
286
+ "õ": 182,
287
+ "ö": 183,
288
+ "÷": 184,
289
+ "ø": 185,
290
+ "ù": 186,
291
+ "ú": 187,
292
+ "û": 188,
293
+ "ü": 189,
294
+ "ý": 190,
295
+ "þ": 191,
296
+ "ÿ": 192,
297
+ "Ā": 193,
298
+ "ā": 194,
299
+ "Ă": 195,
300
+ "ă": 196,
301
+ "Ą": 197,
302
+ "ą": 198,
303
+ "Ć": 199,
304
+ "ć": 200,
305
+ "Ĉ": 201,
306
+ "ĉ": 202,
307
+ "Ċ": 203,
308
+ "ċ": 204,
309
+ "Č": 205,
310
+ "č": 206,
311
+ "Ď": 207,
312
+ "ď": 208,
313
+ "Đ": 209,
314
+ "đ": 210,
315
+ "Ē": 211,
316
+ "ē": 212,
317
+ "Ĕ": 213,
318
+ "ĕ": 214,
319
+ "Ė": 215,
320
+ "ė": 216,
321
+ "Ę": 217,
322
+ "ę": 218,
323
+ "Ě": 219,
324
+ "ě": 220,
325
+ "Ĝ": 221,
326
+ "ĝ": 222,
327
+ "Ğ": 223,
328
+ "ğ": 224,
329
+ "Ġ": 225,
330
+ "ġ": 226,
331
+ "Ģ": 227,
332
+ "ģ": 228,
333
+ "Ĥ": 229,
334
+ "ĥ": 230,
335
+ "Ħ": 231,
336
+ "ħ": 232,
337
+ "Ĩ": 233,
338
+ "ĩ": 234,
339
+ "Ī": 235,
340
+ "ī": 236,
341
+ "Ĭ": 237,
342
+ "ĭ": 238,
343
+ "Į": 239,
344
+ "į": 240,
345
+ "İ": 241,
346
+ "ı": 242,
347
+ "IJ": 243,
348
+ "ij": 244,
349
+ "Ĵ": 245,
350
+ "ĵ": 246,
351
+ "Ķ": 247,
352
+ "ķ": 248,
353
+ "ĸ": 249,
354
+ "Ĺ": 250,
355
+ "ĺ": 251,
356
+ "Ļ": 252,
357
+ "ļ": 253,
358
+ "Ľ": 254,
359
+ "ľ": 255,
360
+ "Ŀ": 256,
361
+ "ŀ": 257,
362
+ "Ł": 258,
363
+ "ł": 259,
364
+ "Ń": 260,
365
+ "à®": 261,
366
+ "à¯": 262,
367
+ "à¯į": 263,
368
+ "Ġà®": 264,
369
+ "ன": 265,
370
+ "à®ķ": 266,
371
+ "à¯ģ": 267,
372
+ "ி": 268,
373
+ "ப": 269,
374
+ "à®±": 270,
375
+ "à®Ł": 271,
376
+ "த": 272,
377
+ "à®®": 273,
378
+ "ா": 274,
379
+ "Ġà®ĩ": 275,
380
+ "ய": 276,
381
+ "Ġவ": 277,
382
+ "à®ªà®Ł": 278,
383
+ "İப": 279,
384
+ "ண": 280,
385
+ "à®°": 281,
386
+ "ல": 282,
387
+ "à¯Ī": 283,
388
+ "Ġந": 284,
389
+ "Ġà®İப": 285,
390
+ "à®ķà®®": 286,
391
+ "Ġà®ĩன": 287,
392
+ "Ġà®ĩà®°": 288,
393
+ "AI": 289,
394
+ "à¯Ĩ": 290,
395
+ "à¯ĩ": 291,
396
+ "à¯į:": 292,
397
+ "à¯į?": 293,
398
+ "Ġà®®": 294,
399
+ "Ġà®ī": 295,
400
+ "Ġà®ļ": 296,
401
+ "றத": 297,
402
+ "தன": 298,
403
+ "மன": 299,
404
+ "Ġவண": 300,
405
+ "Ġவணà®ķ": 301
406
+ },
407
+ "merges": [
408
+ [
409
+ "à",
410
+ "®"
411
+ ],
412
+ [
413
+ "à",
414
+ "¯"
415
+ ],
416
+ [
417
+ "à¯",
418
+ "į"
419
+ ],
420
+ [
421
+ "Ġ",
422
+ "à®"
423
+ ],
424
+ [
425
+ "à®",
426
+ "©"
427
+ ],
428
+ [
429
+ "à®",
430
+ "ķ"
431
+ ],
432
+ [
433
+ "à¯",
434
+ "ģ"
435
+ ],
436
+ [
437
+ "à®",
438
+ "¿"
439
+ ],
440
+ [
441
+ "à®",
442
+ "ª"
443
+ ],
444
+ [
445
+ "à®",
446
+ "±"
447
+ ],
448
+ [
449
+ "à®",
450
+ "Ł"
451
+ ],
452
+ [
453
+ "à®",
454
+ "¤"
455
+ ],
456
+ [
457
+ "à®",
458
+ "®"
459
+ ],
460
+ [
461
+ "à®",
462
+ "¾"
463
+ ],
464
+ [
465
+ "Ġà®",
466
+ "ĩ"
467
+ ],
468
+ [
469
+ "à®",
470
+ "¯"
471
+ ],
472
+ [
473
+ "Ġà®",
474
+ "µ"
475
+ ],
476
+ [
477
+ "ப",
478
+ "à®Ł"
479
+ ],
480
+ [
481
+ "İ",
482
+ "ப"
483
+ ],
484
+ [
485
+ "à®",
486
+ "£"
487
+ ],
488
+ [
489
+ "à®",
490
+ "°"
491
+ ],
492
+ [
493
+ "à®",
494
+ "²"
495
+ ],
496
+ [
497
+ "à¯",
498
+ "Ī"
499
+ ],
500
+ [
501
+ "Ġà®",
502
+ "¨"
503
+ ],
504
+ [
505
+ "Ġà®",
506
+ "İப"
507
+ ],
508
+ [
509
+ "à®ķ",
510
+ "à®®"
511
+ ],
512
+ [
513
+ "Ġà®ĩ",
514
+ "ன"
515
+ ],
516
+ [
517
+ "Ġà®ĩ",
518
+ "à®°"
519
+ ],
520
+ [
521
+ "A",
522
+ "I"
523
+ ],
524
+ [
525
+ "à¯",
526
+ "Ĩ"
527
+ ],
528
+ [
529
+ "à¯",
530
+ "ĩ"
531
+ ],
532
+ [
533
+ "à¯į",
534
+ ":"
535
+ ],
536
+ [
537
+ "à¯į",
538
+ "?"
539
+ ],
540
+ [
541
+ "Ġà®",
542
+ "®"
543
+ ],
544
+ [
545
+ "Ġà®",
546
+ "ī"
547
+ ],
548
+ [
549
+ "Ġà®",
550
+ "ļ"
551
+ ],
552
+ [
553
+ "à®±",
554
+ "த"
555
+ ],
556
+ [
557
+ "த",
558
+ "ன"
559
+ ],
560
+ [
561
+ "à®®",
562
+ "ன"
563
+ ],
564
+ [
565
+ "Ġவ",
566
+ "ண"
567
+ ],
568
+ [
569
+ "Ġவண",
570
+ "à®ķ"
571
+ ]
572
+ ]
573
+ }
574
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "TokenizersBackend",
9
+ "unk_token": "<unk>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b25bcc4e90b14460bee5f236f81b51d7f5d97105ff4966e92de96287f157fb1
3
+ size 5265