LH-Tech-AI commited on
Commit
e331ffe
·
verified ·
1 Parent(s): 70b6ac0

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "head_dim": 24,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 96,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 192,
15
+ "max_position_embeddings": 256,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 4,
19
+ "num_hidden_layers": 4,
20
+ "num_key_value_heads": 4,
21
+ "pad_token_id": 1,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_parameters": {
25
+ "rope_theta": 10000.0,
26
+ "rope_type": "default"
27
+ },
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "5.0.0",
30
+ "use_cache": false,
31
+ "vocab_size": 500
32
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.0.0",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fce3f379b5c485d25f72364d10fd8d9fe22a1f38e244531391e77272cb79404
3
+ size 1866072
tokenizer.json ADDED
@@ -0,0 +1,1532 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<s>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "ByteLevel",
46
+ "add_prefix_space": false,
47
+ "trim_offsets": true,
48
+ "use_regex": true
49
+ },
50
+ "post_processor": {
51
+ "type": "ByteLevel",
52
+ "add_prefix_space": true,
53
+ "trim_offsets": false,
54
+ "use_regex": true
55
+ },
56
+ "decoder": {
57
+ "type": "ByteLevel",
58
+ "add_prefix_space": true,
59
+ "trim_offsets": true,
60
+ "use_regex": true
61
+ },
62
+ "model": {
63
+ "type": "BPE",
64
+ "dropout": null,
65
+ "unk_token": null,
66
+ "continuing_subword_prefix": "",
67
+ "end_of_word_suffix": "",
68
+ "fuse_unk": false,
69
+ "byte_fallback": false,
70
+ "ignore_merges": false,
71
+ "vocab": {
72
+ "<s>": 0,
73
+ "<pad>": 1,
74
+ "</s>": 2,
75
+ "<unk>": 3,
76
+ "<mask>": 4,
77
+ "!": 5,
78
+ "\"": 6,
79
+ "#": 7,
80
+ "$": 8,
81
+ "%": 9,
82
+ "&": 10,
83
+ "'": 11,
84
+ "(": 12,
85
+ ")": 13,
86
+ "*": 14,
87
+ "+": 15,
88
+ ",": 16,
89
+ "-": 17,
90
+ ".": 18,
91
+ "/": 19,
92
+ "0": 20,
93
+ "1": 21,
94
+ "2": 22,
95
+ "3": 23,
96
+ "4": 24,
97
+ "5": 25,
98
+ "6": 26,
99
+ "7": 27,
100
+ "8": 28,
101
+ "9": 29,
102
+ ":": 30,
103
+ ";": 31,
104
+ "<": 32,
105
+ "=": 33,
106
+ ">": 34,
107
+ "?": 35,
108
+ "@": 36,
109
+ "A": 37,
110
+ "B": 38,
111
+ "C": 39,
112
+ "D": 40,
113
+ "E": 41,
114
+ "F": 42,
115
+ "G": 43,
116
+ "H": 44,
117
+ "I": 45,
118
+ "J": 46,
119
+ "K": 47,
120
+ "L": 48,
121
+ "M": 49,
122
+ "N": 50,
123
+ "O": 51,
124
+ "P": 52,
125
+ "Q": 53,
126
+ "R": 54,
127
+ "S": 55,
128
+ "T": 56,
129
+ "U": 57,
130
+ "V": 58,
131
+ "W": 59,
132
+ "X": 60,
133
+ "Y": 61,
134
+ "Z": 62,
135
+ "[": 63,
136
+ "\\": 64,
137
+ "]": 65,
138
+ "^": 66,
139
+ "_": 67,
140
+ "`": 68,
141
+ "a": 69,
142
+ "b": 70,
143
+ "c": 71,
144
+ "d": 72,
145
+ "e": 73,
146
+ "f": 74,
147
+ "g": 75,
148
+ "h": 76,
149
+ "i": 77,
150
+ "j": 78,
151
+ "k": 79,
152
+ "l": 80,
153
+ "m": 81,
154
+ "n": 82,
155
+ "o": 83,
156
+ "p": 84,
157
+ "q": 85,
158
+ "r": 86,
159
+ "s": 87,
160
+ "t": 88,
161
+ "u": 89,
162
+ "v": 90,
163
+ "w": 91,
164
+ "x": 92,
165
+ "y": 93,
166
+ "z": 94,
167
+ "{": 95,
168
+ "|": 96,
169
+ "}": 97,
170
+ "~": 98,
171
+ "¡": 99,
172
+ "¢": 100,
173
+ "£": 101,
174
+ "¤": 102,
175
+ "¥": 103,
176
+ "¦": 104,
177
+ "§": 105,
178
+ "¨": 106,
179
+ "©": 107,
180
+ "ª": 108,
181
+ "«": 109,
182
+ "¬": 110,
183
+ "®": 111,
184
+ "¯": 112,
185
+ "°": 113,
186
+ "±": 114,
187
+ "²": 115,
188
+ "³": 116,
189
+ "´": 117,
190
+ "µ": 118,
191
+ "¶": 119,
192
+ "·": 120,
193
+ "¸": 121,
194
+ "¹": 122,
195
+ "º": 123,
196
+ "»": 124,
197
+ "¼": 125,
198
+ "½": 126,
199
+ "¾": 127,
200
+ "¿": 128,
201
+ "À": 129,
202
+ "Á": 130,
203
+ "Â": 131,
204
+ "Ã": 132,
205
+ "Ä": 133,
206
+ "Å": 134,
207
+ "Æ": 135,
208
+ "Ç": 136,
209
+ "È": 137,
210
+ "É": 138,
211
+ "Ê": 139,
212
+ "Ë": 140,
213
+ "Ì": 141,
214
+ "Í": 142,
215
+ "Î": 143,
216
+ "Ï": 144,
217
+ "Ð": 145,
218
+ "Ñ": 146,
219
+ "Ò": 147,
220
+ "Ó": 148,
221
+ "Ô": 149,
222
+ "Õ": 150,
223
+ "Ö": 151,
224
+ "×": 152,
225
+ "Ø": 153,
226
+ "Ù": 154,
227
+ "Ú": 155,
228
+ "Û": 156,
229
+ "Ü": 157,
230
+ "Ý": 158,
231
+ "Þ": 159,
232
+ "ß": 160,
233
+ "à": 161,
234
+ "á": 162,
235
+ "â": 163,
236
+ "ã": 164,
237
+ "ä": 165,
238
+ "å": 166,
239
+ "æ": 167,
240
+ "ç": 168,
241
+ "è": 169,
242
+ "é": 170,
243
+ "ê": 171,
244
+ "ë": 172,
245
+ "ì": 173,
246
+ "í": 174,
247
+ "î": 175,
248
+ "ï": 176,
249
+ "ð": 177,
250
+ "ñ": 178,
251
+ "ò": 179,
252
+ "ó": 180,
253
+ "ô": 181,
254
+ "õ": 182,
255
+ "ö": 183,
256
+ "÷": 184,
257
+ "ø": 185,
258
+ "ù": 186,
259
+ "ú": 187,
260
+ "û": 188,
261
+ "ü": 189,
262
+ "ý": 190,
263
+ "þ": 191,
264
+ "ÿ": 192,
265
+ "Ā": 193,
266
+ "ā": 194,
267
+ "Ă": 195,
268
+ "ă": 196,
269
+ "Ą": 197,
270
+ "ą": 198,
271
+ "Ć": 199,
272
+ "ć": 200,
273
+ "Ĉ": 201,
274
+ "ĉ": 202,
275
+ "Ċ": 203,
276
+ "ċ": 204,
277
+ "Č": 205,
278
+ "č": 206,
279
+ "Ď": 207,
280
+ "ď": 208,
281
+ "Đ": 209,
282
+ "đ": 210,
283
+ "Ē": 211,
284
+ "ē": 212,
285
+ "Ĕ": 213,
286
+ "ĕ": 214,
287
+ "Ė": 215,
288
+ "ė": 216,
289
+ "Ę": 217,
290
+ "ę": 218,
291
+ "Ě": 219,
292
+ "ě": 220,
293
+ "Ĝ": 221,
294
+ "ĝ": 222,
295
+ "Ğ": 223,
296
+ "ğ": 224,
297
+ "Ġ": 225,
298
+ "ġ": 226,
299
+ "Ģ": 227,
300
+ "ģ": 228,
301
+ "Ĥ": 229,
302
+ "ĥ": 230,
303
+ "Ħ": 231,
304
+ "ħ": 232,
305
+ "Ĩ": 233,
306
+ "ĩ": 234,
307
+ "Ī": 235,
308
+ "ī": 236,
309
+ "Ĭ": 237,
310
+ "ĭ": 238,
311
+ "Į": 239,
312
+ "į": 240,
313
+ "İ": 241,
314
+ "ı": 242,
315
+ "IJ": 243,
316
+ "ij": 244,
317
+ "Ĵ": 245,
318
+ "ĵ": 246,
319
+ "Ķ": 247,
320
+ "ķ": 248,
321
+ "ĸ": 249,
322
+ "Ĺ": 250,
323
+ "ĺ": 251,
324
+ "Ļ": 252,
325
+ "ļ": 253,
326
+ "Ľ": 254,
327
+ "ľ": 255,
328
+ "Ŀ": 256,
329
+ "ŀ": 257,
330
+ "Ł": 258,
331
+ "ł": 259,
332
+ "Ń": 260,
333
+ "Ġt": 261,
334
+ "Ġa": 262,
335
+ "he": 263,
336
+ "in": 264,
337
+ "re": 265,
338
+ "Ġthe": 266,
339
+ "on": 267,
340
+ "er": 268,
341
+ "Ġo": 269,
342
+ "at": 270,
343
+ "Ġs": 271,
344
+ "en": 272,
345
+ "Ġc": 273,
346
+ "Ġw": 274,
347
+ "es": 275,
348
+ "is": 276,
349
+ "nd": 277,
350
+ "it": 278,
351
+ "or": 279,
352
+ "Ġp": 280,
353
+ "al": 281,
354
+ "ed": 282,
355
+ "Ġb": 283,
356
+ "an": 284,
357
+ "Ġof": 285,
358
+ "Ġf": 286,
359
+ "ing": 287,
360
+ "Ġin": 288,
361
+ "ar": 289,
362
+ "ou": 290,
363
+ "Ġm": 291,
364
+ "Ġand": 292,
365
+ "Ġto": 293,
366
+ "ic": 294,
367
+ "Ġd": 295,
368
+ "ion": 296,
369
+ "le": 297,
370
+ "ro": 298,
371
+ "as": 299,
372
+ "Ġh": 300,
373
+ "Ġth": 301,
374
+ "ent": 302,
375
+ "ct": 303,
376
+ "Ġe": 304,
377
+ "il": 305,
378
+ "Ġre": 306,
379
+ "om": 307,
380
+ "ve": 308,
381
+ "Ġl": 309,
382
+ "st": 310,
383
+ "Ġn": 311,
384
+ "ly": 312,
385
+ "âĢ": 313,
386
+ "Ġbe": 314,
387
+ "Ġis": 315,
388
+ "ĠT": 316,
389
+ "se": 317,
390
+ "ol": 318,
391
+ "Ġg": 319,
392
+ "ation": 320,
393
+ "im": 321,
394
+ "id": 322,
395
+ "et": 323,
396
+ "ut": 324,
397
+ "ur": 325,
398
+ "ce": 326,
399
+ "ot": 327,
400
+ "ra": 328,
401
+ "ow": 329,
402
+ "ch": 330,
403
+ "ĠA": 331,
404
+ "Ġfor": 332,
405
+ "ig": 333,
406
+ "ĠS": 334,
407
+ "Ġthat": 335,
408
+ "Ġu": 336,
409
+ "Ġon": 337,
410
+ "Ġst": 338,
411
+ "ver": 339,
412
+ "ĠC": 340,
413
+ "ĠI": 341,
414
+ "ir": 342,
415
+ "Ġy": 343,
416
+ "ul": 344,
417
+ "ay": 345,
418
+ "am": 346,
419
+ "Ġas": 347,
420
+ "ith": 348,
421
+ "el": 349,
422
+ "ad": 350,
423
+ "her": 351,
424
+ "Ġpro": 352,
425
+ "Ġare": 353,
426
+ "Ġcon": 354,
427
+ "Ġan": 355,
428
+ "Ġwith": 356,
429
+ "Ġwh": 357,
430
+ "if": 358,
431
+ "Ġit": 359,
432
+ "Ġor": 360,
433
+ "Ġal": 361,
434
+ "Ġyou": 362,
435
+ "ter": 363,
436
+ "od": 364,
437
+ "ĠM": 365,
438
+ "Ġ(": 366,
439
+ "ĠThe": 367,
440
+ "ment": 368,
441
+ "ge": 369,
442
+ "ĠP": 370,
443
+ "Ġ1": 371,
444
+ "th": 372,
445
+ "ate": 373,
446
+ "op": 374,
447
+ "ist": 375,
448
+ "ers": 376,
449
+ "Ġde": 377,
450
+ "ies": 378,
451
+ "ab": 379,
452
+ "ill": 380,
453
+ "Ġhe": 381,
454
+ "ess": 382,
455
+ "ĠB": 383,
456
+ "Ġex": 384,
457
+ "us": 385,
458
+ "Ġwe": 386,
459
+ "ect": 387,
460
+ "ore": 388,
461
+ "Ġsu": 389,
462
+ "Ġcom": 390,
463
+ "âĢĻ": 391,
464
+ "ity": 392,
465
+ "est": 393,
466
+ "ive": 394,
467
+ "res": 395,
468
+ "Ġha": 396,
469
+ "ac": 397,
470
+ "rom": 398,
471
+ "ld": 399,
472
+ "ĠH": 400,
473
+ "os": 401,
474
+ "um": 402,
475
+ "Ġv": 403,
476
+ "ke": 404,
477
+ "Ġby": 405,
478
+ "em": 406,
479
+ "ant": 407,
480
+ "iv": 408,
481
+ "qu": 409,
482
+ "ain": 410,
483
+ "Ġat": 411,
484
+ "nt": 412,
485
+ "ĠW": 413,
486
+ "pp": 414,
487
+ "Ġwas": 415,
488
+ "ĠD": 416,
489
+ "igh": 417,
490
+ "ud": 418,
491
+ "ĠE": 419,
492
+ "Ġfrom": 420,
493
+ "Ġcan": 421,
494
+ "and": 422,
495
+ "oc": 423,
496
+ "Ġch": 424,
497
+ "Ġr": 425,
498
+ "ĠR": 426,
499
+ "ort": 427,
500
+ "Ġne": 428,
501
+ "ĠF": 429,
502
+ "Ġse": 430,
503
+ "ial": 431,
504
+ "Ġ2": 432,
505
+ "ure": 433,
506
+ "ĠâĢ": 434,
507
+ "Ġnot": 435,
508
+ "un": 436,
509
+ "art": 437,
510
+ "ĠN": 438,
511
+ "Ġle": 439,
512
+ "ical": 440,
513
+ "ĠG": 441,
514
+ "Ġhave": 442,
515
+ "ri": 443,
516
+ "ĠL": 444,
517
+ "Ġsh": 445,
518
+ "og": 446,
519
+ "Ġen": 447,
520
+ "Ġthis": 448,
521
+ "Ġsp": 449,
522
+ "00": 450,
523
+ "pt": 451,
524
+ "ight": 452,
525
+ "rou": 453,
526
+ "Ġab": 454,
527
+ "red": 455,
528
+ "ich": 456,
529
+ "all": 457,
530
+ "Ġwor": 458,
531
+ "ther": 459,
532
+ "ould": 460,
533
+ "The": 461,
534
+ "gh": 462,
535
+ "ions": 463,
536
+ "our": 464,
537
+ "ome": 465,
538
+ "ost": 466,
539
+ "du": 467,
540
+ "ated": 468,
541
+ "Ġim": 469,
542
+ "Ġus": 470,
543
+ "ine": 471,
544
+ "per": 472,
545
+ "out": 473,
546
+ "ard": 474,
547
+ "Ġpl": 475,
548
+ "ag": 476,
549
+ "Ġtheir": 477,
550
+ "ide": 478,
551
+ "ell": 479,
552
+ "ff": 480,
553
+ "act": 481,
554
+ "ans": 482,
555
+ "ĠO": 483,
556
+ "Ġint": 484,
557
+ "ast": 485,
558
+ "pl": 486,
559
+ "ear": 487,
560
+ "age": 488,
561
+ "ust": 489,
562
+ "ĠJ": 490,
563
+ "Ġwhich": 491,
564
+ "ak": 492,
565
+ "Ġk": 493,
566
+ "ous": 494,
567
+ "Ġwhe": 495,
568
+ "ec": 496,
569
+ "Ġthey": 497,
570
+ "ĠU": 498,
571
+ "iz": 499
572
+ },
573
+ "merges": [
574
+ [
575
+ "Ġ",
576
+ "t"
577
+ ],
578
+ [
579
+ "Ġ",
580
+ "a"
581
+ ],
582
+ [
583
+ "h",
584
+ "e"
585
+ ],
586
+ [
587
+ "i",
588
+ "n"
589
+ ],
590
+ [
591
+ "r",
592
+ "e"
593
+ ],
594
+ [
595
+ "Ġt",
596
+ "he"
597
+ ],
598
+ [
599
+ "o",
600
+ "n"
601
+ ],
602
+ [
603
+ "e",
604
+ "r"
605
+ ],
606
+ [
607
+ "Ġ",
608
+ "o"
609
+ ],
610
+ [
611
+ "a",
612
+ "t"
613
+ ],
614
+ [
615
+ "Ġ",
616
+ "s"
617
+ ],
618
+ [
619
+ "e",
620
+ "n"
621
+ ],
622
+ [
623
+ "Ġ",
624
+ "c"
625
+ ],
626
+ [
627
+ "Ġ",
628
+ "w"
629
+ ],
630
+ [
631
+ "e",
632
+ "s"
633
+ ],
634
+ [
635
+ "i",
636
+ "s"
637
+ ],
638
+ [
639
+ "n",
640
+ "d"
641
+ ],
642
+ [
643
+ "i",
644
+ "t"
645
+ ],
646
+ [
647
+ "o",
648
+ "r"
649
+ ],
650
+ [
651
+ "Ġ",
652
+ "p"
653
+ ],
654
+ [
655
+ "a",
656
+ "l"
657
+ ],
658
+ [
659
+ "e",
660
+ "d"
661
+ ],
662
+ [
663
+ "Ġ",
664
+ "b"
665
+ ],
666
+ [
667
+ "a",
668
+ "n"
669
+ ],
670
+ [
671
+ "Ġo",
672
+ "f"
673
+ ],
674
+ [
675
+ "Ġ",
676
+ "f"
677
+ ],
678
+ [
679
+ "in",
680
+ "g"
681
+ ],
682
+ [
683
+ "Ġ",
684
+ "in"
685
+ ],
686
+ [
687
+ "a",
688
+ "r"
689
+ ],
690
+ [
691
+ "o",
692
+ "u"
693
+ ],
694
+ [
695
+ "Ġ",
696
+ "m"
697
+ ],
698
+ [
699
+ "Ġa",
700
+ "nd"
701
+ ],
702
+ [
703
+ "Ġt",
704
+ "o"
705
+ ],
706
+ [
707
+ "i",
708
+ "c"
709
+ ],
710
+ [
711
+ "Ġ",
712
+ "d"
713
+ ],
714
+ [
715
+ "i",
716
+ "on"
717
+ ],
718
+ [
719
+ "l",
720
+ "e"
721
+ ],
722
+ [
723
+ "r",
724
+ "o"
725
+ ],
726
+ [
727
+ "a",
728
+ "s"
729
+ ],
730
+ [
731
+ "Ġ",
732
+ "h"
733
+ ],
734
+ [
735
+ "Ġt",
736
+ "h"
737
+ ],
738
+ [
739
+ "en",
740
+ "t"
741
+ ],
742
+ [
743
+ "c",
744
+ "t"
745
+ ],
746
+ [
747
+ "Ġ",
748
+ "e"
749
+ ],
750
+ [
751
+ "i",
752
+ "l"
753
+ ],
754
+ [
755
+ "Ġ",
756
+ "re"
757
+ ],
758
+ [
759
+ "o",
760
+ "m"
761
+ ],
762
+ [
763
+ "v",
764
+ "e"
765
+ ],
766
+ [
767
+ "Ġ",
768
+ "l"
769
+ ],
770
+ [
771
+ "s",
772
+ "t"
773
+ ],
774
+ [
775
+ "Ġ",
776
+ "n"
777
+ ],
778
+ [
779
+ "l",
780
+ "y"
781
+ ],
782
+ [
783
+ "â",
784
+ "Ģ"
785
+ ],
786
+ [
787
+ "Ġb",
788
+ "e"
789
+ ],
790
+ [
791
+ "Ġ",
792
+ "is"
793
+ ],
794
+ [
795
+ "Ġ",
796
+ "T"
797
+ ],
798
+ [
799
+ "s",
800
+ "e"
801
+ ],
802
+ [
803
+ "o",
804
+ "l"
805
+ ],
806
+ [
807
+ "Ġ",
808
+ "g"
809
+ ],
810
+ [
811
+ "at",
812
+ "ion"
813
+ ],
814
+ [
815
+ "i",
816
+ "m"
817
+ ],
818
+ [
819
+ "i",
820
+ "d"
821
+ ],
822
+ [
823
+ "e",
824
+ "t"
825
+ ],
826
+ [
827
+ "u",
828
+ "t"
829
+ ],
830
+ [
831
+ "u",
832
+ "r"
833
+ ],
834
+ [
835
+ "c",
836
+ "e"
837
+ ],
838
+ [
839
+ "o",
840
+ "t"
841
+ ],
842
+ [
843
+ "r",
844
+ "a"
845
+ ],
846
+ [
847
+ "o",
848
+ "w"
849
+ ],
850
+ [
851
+ "c",
852
+ "h"
853
+ ],
854
+ [
855
+ "Ġ",
856
+ "A"
857
+ ],
858
+ [
859
+ "Ġf",
860
+ "or"
861
+ ],
862
+ [
863
+ "i",
864
+ "g"
865
+ ],
866
+ [
867
+ "Ġ",
868
+ "S"
869
+ ],
870
+ [
871
+ "Ġth",
872
+ "at"
873
+ ],
874
+ [
875
+ "Ġ",
876
+ "u"
877
+ ],
878
+ [
879
+ "Ġ",
880
+ "on"
881
+ ],
882
+ [
883
+ "Ġs",
884
+ "t"
885
+ ],
886
+ [
887
+ "v",
888
+ "er"
889
+ ],
890
+ [
891
+ "Ġ",
892
+ "C"
893
+ ],
894
+ [
895
+ "Ġ",
896
+ "I"
897
+ ],
898
+ [
899
+ "i",
900
+ "r"
901
+ ],
902
+ [
903
+ "Ġ",
904
+ "y"
905
+ ],
906
+ [
907
+ "u",
908
+ "l"
909
+ ],
910
+ [
911
+ "a",
912
+ "y"
913
+ ],
914
+ [
915
+ "a",
916
+ "m"
917
+ ],
918
+ [
919
+ "Ġa",
920
+ "s"
921
+ ],
922
+ [
923
+ "it",
924
+ "h"
925
+ ],
926
+ [
927
+ "e",
928
+ "l"
929
+ ],
930
+ [
931
+ "a",
932
+ "d"
933
+ ],
934
+ [
935
+ "he",
936
+ "r"
937
+ ],
938
+ [
939
+ "Ġp",
940
+ "ro"
941
+ ],
942
+ [
943
+ "Ġa",
944
+ "re"
945
+ ],
946
+ [
947
+ "Ġc",
948
+ "on"
949
+ ],
950
+ [
951
+ "Ġa",
952
+ "n"
953
+ ],
954
+ [
955
+ "Ġw",
956
+ "ith"
957
+ ],
958
+ [
959
+ "Ġw",
960
+ "h"
961
+ ],
962
+ [
963
+ "i",
964
+ "f"
965
+ ],
966
+ [
967
+ "Ġ",
968
+ "it"
969
+ ],
970
+ [
971
+ "Ġo",
972
+ "r"
973
+ ],
974
+ [
975
+ "Ġa",
976
+ "l"
977
+ ],
978
+ [
979
+ "Ġy",
980
+ "ou"
981
+ ],
982
+ [
983
+ "t",
984
+ "er"
985
+ ],
986
+ [
987
+ "o",
988
+ "d"
989
+ ],
990
+ [
991
+ "Ġ",
992
+ "M"
993
+ ],
994
+ [
995
+ "Ġ",
996
+ "("
997
+ ],
998
+ [
999
+ "ĠT",
1000
+ "he"
1001
+ ],
1002
+ [
1003
+ "m",
1004
+ "ent"
1005
+ ],
1006
+ [
1007
+ "g",
1008
+ "e"
1009
+ ],
1010
+ [
1011
+ "Ġ",
1012
+ "P"
1013
+ ],
1014
+ [
1015
+ "Ġ",
1016
+ "1"
1017
+ ],
1018
+ [
1019
+ "t",
1020
+ "h"
1021
+ ],
1022
+ [
1023
+ "at",
1024
+ "e"
1025
+ ],
1026
+ [
1027
+ "o",
1028
+ "p"
1029
+ ],
1030
+ [
1031
+ "is",
1032
+ "t"
1033
+ ],
1034
+ [
1035
+ "er",
1036
+ "s"
1037
+ ],
1038
+ [
1039
+ "Ġd",
1040
+ "e"
1041
+ ],
1042
+ [
1043
+ "i",
1044
+ "es"
1045
+ ],
1046
+ [
1047
+ "a",
1048
+ "b"
1049
+ ],
1050
+ [
1051
+ "il",
1052
+ "l"
1053
+ ],
1054
+ [
1055
+ "Ġ",
1056
+ "he"
1057
+ ],
1058
+ [
1059
+ "es",
1060
+ "s"
1061
+ ],
1062
+ [
1063
+ "Ġ",
1064
+ "B"
1065
+ ],
1066
+ [
1067
+ "Ġe",
1068
+ "x"
1069
+ ],
1070
+ [
1071
+ "u",
1072
+ "s"
1073
+ ],
1074
+ [
1075
+ "Ġw",
1076
+ "e"
1077
+ ],
1078
+ [
1079
+ "e",
1080
+ "ct"
1081
+ ],
1082
+ [
1083
+ "o",
1084
+ "re"
1085
+ ],
1086
+ [
1087
+ "Ġs",
1088
+ "u"
1089
+ ],
1090
+ [
1091
+ "Ġc",
1092
+ "om"
1093
+ ],
1094
+ [
1095
+ "âĢ",
1096
+ "Ļ"
1097
+ ],
1098
+ [
1099
+ "it",
1100
+ "y"
1101
+ ],
1102
+ [
1103
+ "es",
1104
+ "t"
1105
+ ],
1106
+ [
1107
+ "i",
1108
+ "ve"
1109
+ ],
1110
+ [
1111
+ "re",
1112
+ "s"
1113
+ ],
1114
+ [
1115
+ "Ġh",
1116
+ "a"
1117
+ ],
1118
+ [
1119
+ "a",
1120
+ "c"
1121
+ ],
1122
+ [
1123
+ "ro",
1124
+ "m"
1125
+ ],
1126
+ [
1127
+ "l",
1128
+ "d"
1129
+ ],
1130
+ [
1131
+ "Ġ",
1132
+ "H"
1133
+ ],
1134
+ [
1135
+ "o",
1136
+ "s"
1137
+ ],
1138
+ [
1139
+ "u",
1140
+ "m"
1141
+ ],
1142
+ [
1143
+ "Ġ",
1144
+ "v"
1145
+ ],
1146
+ [
1147
+ "k",
1148
+ "e"
1149
+ ],
1150
+ [
1151
+ "Ġb",
1152
+ "y"
1153
+ ],
1154
+ [
1155
+ "e",
1156
+ "m"
1157
+ ],
1158
+ [
1159
+ "an",
1160
+ "t"
1161
+ ],
1162
+ [
1163
+ "i",
1164
+ "v"
1165
+ ],
1166
+ [
1167
+ "q",
1168
+ "u"
1169
+ ],
1170
+ [
1171
+ "a",
1172
+ "in"
1173
+ ],
1174
+ [
1175
+ "Ġa",
1176
+ "t"
1177
+ ],
1178
+ [
1179
+ "n",
1180
+ "t"
1181
+ ],
1182
+ [
1183
+ "Ġ",
1184
+ "W"
1185
+ ],
1186
+ [
1187
+ "p",
1188
+ "p"
1189
+ ],
1190
+ [
1191
+ "Ġw",
1192
+ "as"
1193
+ ],
1194
+ [
1195
+ "Ġ",
1196
+ "D"
1197
+ ],
1198
+ [
1199
+ "ig",
1200
+ "h"
1201
+ ],
1202
+ [
1203
+ "u",
1204
+ "d"
1205
+ ],
1206
+ [
1207
+ "Ġ",
1208
+ "E"
1209
+ ],
1210
+ [
1211
+ "Ġf",
1212
+ "rom"
1213
+ ],
1214
+ [
1215
+ "Ġc",
1216
+ "an"
1217
+ ],
1218
+ [
1219
+ "a",
1220
+ "nd"
1221
+ ],
1222
+ [
1223
+ "o",
1224
+ "c"
1225
+ ],
1226
+ [
1227
+ "Ġc",
1228
+ "h"
1229
+ ],
1230
+ [
1231
+ "Ġ",
1232
+ "r"
1233
+ ],
1234
+ [
1235
+ "Ġ",
1236
+ "R"
1237
+ ],
1238
+ [
1239
+ "or",
1240
+ "t"
1241
+ ],
1242
+ [
1243
+ "Ġn",
1244
+ "e"
1245
+ ],
1246
+ [
1247
+ "Ġ",
1248
+ "F"
1249
+ ],
1250
+ [
1251
+ "Ġs",
1252
+ "e"
1253
+ ],
1254
+ [
1255
+ "i",
1256
+ "al"
1257
+ ],
1258
+ [
1259
+ "Ġ",
1260
+ "2"
1261
+ ],
1262
+ [
1263
+ "u",
1264
+ "re"
1265
+ ],
1266
+ [
1267
+ "Ġ",
1268
+ "âĢ"
1269
+ ],
1270
+ [
1271
+ "Ġn",
1272
+ "ot"
1273
+ ],
1274
+ [
1275
+ "u",
1276
+ "n"
1277
+ ],
1278
+ [
1279
+ "ar",
1280
+ "t"
1281
+ ],
1282
+ [
1283
+ "Ġ",
1284
+ "N"
1285
+ ],
1286
+ [
1287
+ "Ġ",
1288
+ "le"
1289
+ ],
1290
+ [
1291
+ "ic",
1292
+ "al"
1293
+ ],
1294
+ [
1295
+ "Ġ",
1296
+ "G"
1297
+ ],
1298
+ [
1299
+ "Ġha",
1300
+ "ve"
1301
+ ],
1302
+ [
1303
+ "r",
1304
+ "i"
1305
+ ],
1306
+ [
1307
+ "Ġ",
1308
+ "L"
1309
+ ],
1310
+ [
1311
+ "Ġs",
1312
+ "h"
1313
+ ],
1314
+ [
1315
+ "o",
1316
+ "g"
1317
+ ],
1318
+ [
1319
+ "Ġ",
1320
+ "en"
1321
+ ],
1322
+ [
1323
+ "Ġth",
1324
+ "is"
1325
+ ],
1326
+ [
1327
+ "Ġs",
1328
+ "p"
1329
+ ],
1330
+ [
1331
+ "0",
1332
+ "0"
1333
+ ],
1334
+ [
1335
+ "p",
1336
+ "t"
1337
+ ],
1338
+ [
1339
+ "igh",
1340
+ "t"
1341
+ ],
1342
+ [
1343
+ "r",
1344
+ "ou"
1345
+ ],
1346
+ [
1347
+ "Ġa",
1348
+ "b"
1349
+ ],
1350
+ [
1351
+ "re",
1352
+ "d"
1353
+ ],
1354
+ [
1355
+ "ic",
1356
+ "h"
1357
+ ],
1358
+ [
1359
+ "al",
1360
+ "l"
1361
+ ],
1362
+ [
1363
+ "Ġw",
1364
+ "or"
1365
+ ],
1366
+ [
1367
+ "t",
1368
+ "her"
1369
+ ],
1370
+ [
1371
+ "ou",
1372
+ "ld"
1373
+ ],
1374
+ [
1375
+ "T",
1376
+ "he"
1377
+ ],
1378
+ [
1379
+ "g",
1380
+ "h"
1381
+ ],
1382
+ [
1383
+ "ion",
1384
+ "s"
1385
+ ],
1386
+ [
1387
+ "ou",
1388
+ "r"
1389
+ ],
1390
+ [
1391
+ "om",
1392
+ "e"
1393
+ ],
1394
+ [
1395
+ "o",
1396
+ "st"
1397
+ ],
1398
+ [
1399
+ "d",
1400
+ "u"
1401
+ ],
1402
+ [
1403
+ "at",
1404
+ "ed"
1405
+ ],
1406
+ [
1407
+ "Ġ",
1408
+ "im"
1409
+ ],
1410
+ [
1411
+ "Ġu",
1412
+ "s"
1413
+ ],
1414
+ [
1415
+ "in",
1416
+ "e"
1417
+ ],
1418
+ [
1419
+ "p",
1420
+ "er"
1421
+ ],
1422
+ [
1423
+ "ou",
1424
+ "t"
1425
+ ],
1426
+ [
1427
+ "ar",
1428
+ "d"
1429
+ ],
1430
+ [
1431
+ "Ġp",
1432
+ "l"
1433
+ ],
1434
+ [
1435
+ "a",
1436
+ "g"
1437
+ ],
1438
+ [
1439
+ "Ġthe",
1440
+ "ir"
1441
+ ],
1442
+ [
1443
+ "id",
1444
+ "e"
1445
+ ],
1446
+ [
1447
+ "el",
1448
+ "l"
1449
+ ],
1450
+ [
1451
+ "f",
1452
+ "f"
1453
+ ],
1454
+ [
1455
+ "a",
1456
+ "ct"
1457
+ ],
1458
+ [
1459
+ "an",
1460
+ "s"
1461
+ ],
1462
+ [
1463
+ "Ġ",
1464
+ "O"
1465
+ ],
1466
+ [
1467
+ "Ġin",
1468
+ "t"
1469
+ ],
1470
+ [
1471
+ "as",
1472
+ "t"
1473
+ ],
1474
+ [
1475
+ "p",
1476
+ "l"
1477
+ ],
1478
+ [
1479
+ "e",
1480
+ "ar"
1481
+ ],
1482
+ [
1483
+ "a",
1484
+ "ge"
1485
+ ],
1486
+ [
1487
+ "u",
1488
+ "st"
1489
+ ],
1490
+ [
1491
+ "Ġ",
1492
+ "J"
1493
+ ],
1494
+ [
1495
+ "Ġwh",
1496
+ "ich"
1497
+ ],
1498
+ [
1499
+ "a",
1500
+ "k"
1501
+ ],
1502
+ [
1503
+ "Ġ",
1504
+ "k"
1505
+ ],
1506
+ [
1507
+ "ou",
1508
+ "s"
1509
+ ],
1510
+ [
1511
+ "Ġw",
1512
+ "he"
1513
+ ],
1514
+ [
1515
+ "e",
1516
+ "c"
1517
+ ],
1518
+ [
1519
+ "Ġthe",
1520
+ "y"
1521
+ ],
1522
+ [
1523
+ "Ġ",
1524
+ "U"
1525
+ ],
1526
+ [
1527
+ "i",
1528
+ "z"
1529
+ ]
1530
+ ]
1531
+ }
1532
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<pad>",
7
+ "tokenizer_class": "TokenizersBackend",
8
+ "unk_token": "<unk>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d35bbf17c5310ec66948914f6ae69967c88a4687b5d1ec91c297699c56f61be
3
+ size 5137