francois-meyer commited on
Commit
5ca92f0
·
verified ·
1 Parent(s): 4423f0a

Upload main checkpoint (epoch_1B)

Browse files
Files changed (6) hide show
  1. config.json +44 -0
  2. lexicon.json +0 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +23 -0
  5. tokenizer_config.json +74 -0
  6. vocab.json +746 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SubSegDeBERTaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "char_decoder_hidden_size": 256,
8
+ "char_decoder_num_layers": 1,
9
+ "char_embed_dim": 128,
10
+ "cls_token_id": 1,
11
+ "dropout": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 2,
14
+ "eow_token_id": 5,
15
+ "hidden_act": "gelu",
16
+ "hidden_dropout_prob": 0.1,
17
+ "hidden_size": 768,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 3072,
20
+ "layer_norm_eps": 1e-07,
21
+ "lex_vocab_size": 40001,
22
+ "loss_normalization": "word",
23
+ "mask_token_id": 3,
24
+ "max_position_embeddings": 1024,
25
+ "max_relative_positions": -1,
26
+ "max_seg_len": 5,
27
+ "mlm_probability": 0.3,
28
+ "model_type": "subsegdeberta",
29
+ "n_alpha": 426,
30
+ "norm_rel_ebd": "layer_norm",
31
+ "num_attention_heads": 12,
32
+ "num_hidden_layers": 12,
33
+ "pad_token_id": 0,
34
+ "pos_att_type": "p2c|c2p",
35
+ "position_buckets": 256,
36
+ "relative_attention": true,
37
+ "seg_end_token_id": 6,
38
+ "sep_token_id": 2,
39
+ "transformers_version": "4.57.1",
40
+ "unk_token_id": 4,
41
+ "vocab_size": 744,
42
+ "word_context_hidden_size": 768,
43
+ "word_context_num_layers": 1
44
+ }
lexicon.json ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e2472d3a71bafd95bb0b096f5c119ca358c2e02223813c5eed3942e0a537ccb
3
+ size 561618648
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<eow>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<seg>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "cls_token": "<cls>",
19
+ "mask_token": "<mask>",
20
+ "pad_token": "<pad>",
21
+ "sep_token": "<sep>",
22
+ "unk_token": "<unk>"
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<cls>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<sep>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<mask>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<eow>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<seg>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<eow>",
62
+ "<seg>"
63
+ ],
64
+ "clean_up_tokenization_spaces": false,
65
+ "cls_token": "<cls>",
66
+ "extra_special_tokens": {},
67
+ "mask_token": "<mask>",
68
+ "max_seg_len": 5,
69
+ "model_max_length": 1024,
70
+ "pad_token": "<pad>",
71
+ "sep_token": "<sep>",
72
+ "tokenizer_class": "SubSegDeBERTaTokenizer",
73
+ "unk_token": "<unk>"
74
+ }
vocab.json ADDED
@@ -0,0 +1,746 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 0,
3
+ "<cls>": 1,
4
+ "<sep>": 2,
5
+ "<mask>": 3,
6
+ "<unk>": 4,
7
+ "<eow>": 5,
8
+ "<seg>": 6,
9
+ "A": 7,
10
+ "B": 8,
11
+ "C": 9,
12
+ "D": 10,
13
+ "E": 11,
14
+ "F": 12,
15
+ "G": 13,
16
+ "H": 14,
17
+ "I": 15,
18
+ "J": 16,
19
+ "K": 17,
20
+ "L": 18,
21
+ "M": 19,
22
+ "N": 20,
23
+ "O": 21,
24
+ "P": 22,
25
+ "Q": 23,
26
+ "R": 24,
27
+ "S": 25,
28
+ "T": 26,
29
+ "U": 27,
30
+ "V": 28,
31
+ "W": 29,
32
+ "X": 30,
33
+ "Y": 31,
34
+ "Z": 32,
35
+ "a": 33,
36
+ "b": 34,
37
+ "c": 35,
38
+ "d": 36,
39
+ "e": 37,
40
+ "f": 38,
41
+ "g": 39,
42
+ "h": 40,
43
+ "i": 41,
44
+ "j": 42,
45
+ "k": 43,
46
+ "l": 44,
47
+ "m": 45,
48
+ "n": 46,
49
+ "o": 47,
50
+ "p": 48,
51
+ "q": 49,
52
+ "r": 50,
53
+ "s": 51,
54
+ "t": 52,
55
+ "u": 53,
56
+ "v": 54,
57
+ "w": 55,
58
+ "x": 56,
59
+ "y": 57,
60
+ "z": 58,
61
+ "º": 59,
62
+ "À": 60,
63
+ "Á": 61,
64
+ "Â": 62,
65
+ "Ã": 63,
66
+ "Ä": 64,
67
+ "Å": 65,
68
+ "Æ": 66,
69
+ "Ç": 67,
70
+ "È": 68,
71
+ "É": 69,
72
+ "Ê": 70,
73
+ "Ë": 71,
74
+ "Ì": 72,
75
+ "Í": 73,
76
+ "Î": 74,
77
+ "Ï": 75,
78
+ "Ð": 76,
79
+ "Ñ": 77,
80
+ "Ò": 78,
81
+ "Ó": 79,
82
+ "Ô": 80,
83
+ "Õ": 81,
84
+ "Ö": 82,
85
+ "Ø": 83,
86
+ "Ù": 84,
87
+ "Ú": 85,
88
+ "Û": 86,
89
+ "Ü": 87,
90
+ "Ý": 88,
91
+ "Þ": 89,
92
+ "ß": 90,
93
+ "à": 91,
94
+ "á": 92,
95
+ "â": 93,
96
+ "ã": 94,
97
+ "ä": 95,
98
+ "å": 96,
99
+ "æ": 97,
100
+ "ç": 98,
101
+ "è": 99,
102
+ "é": 100,
103
+ "ê": 101,
104
+ "ë": 102,
105
+ "ì": 103,
106
+ "í": 104,
107
+ "î": 105,
108
+ "ï": 106,
109
+ "ð": 107,
110
+ "ñ": 108,
111
+ "ò": 109,
112
+ "ó": 110,
113
+ "ô": 111,
114
+ "õ": 112,
115
+ "ö": 113,
116
+ "ø": 114,
117
+ "ù": 115,
118
+ "ú": 116,
119
+ "û": 117,
120
+ "ü": 118,
121
+ "ý": 119,
122
+ "þ": 120,
123
+ "ÿ": 121,
124
+ "Ā": 122,
125
+ "ā": 123,
126
+ "Ă": 124,
127
+ "ă": 125,
128
+ "Ą": 126,
129
+ "ą": 127,
130
+ "Ć": 128,
131
+ "ć": 129,
132
+ "Ĉ": 130,
133
+ "ĉ": 131,
134
+ "Č": 132,
135
+ "č": 133,
136
+ "ď": 134,
137
+ "Đ": 135,
138
+ "đ": 136,
139
+ "Ē": 137,
140
+ "ē": 138,
141
+ "Ĕ": 139,
142
+ "ĕ": 140,
143
+ "Ė": 141,
144
+ "ė": 142,
145
+ "Ę": 143,
146
+ "ę": 144,
147
+ "Ě": 145,
148
+ "ě": 146,
149
+ "Ĝ": 147,
150
+ "ĝ": 148,
151
+ "Ğ": 149,
152
+ "ğ": 150,
153
+ "ġ": 151,
154
+ "ģ": 152,
155
+ "Ĥ": 153,
156
+ "ĥ": 154,
157
+ "Ħ": 155,
158
+ "ħ": 156,
159
+ "ĩ": 157,
160
+ "Ī": 158,
161
+ "ī": 159,
162
+ "ĭ": 160,
163
+ "į": 161,
164
+ "İ": 162,
165
+ "ı": 163,
166
+ "ĵ": 164,
167
+ "Ķ": 165,
168
+ "ķ": 166,
169
+ "ĺ": 167,
170
+ "Ļ": 168,
171
+ "ļ": 169,
172
+ "Ľ": 170,
173
+ "ľ": 171,
174
+ "Ł": 172,
175
+ "ł": 173,
176
+ "Ń": 174,
177
+ "ń": 175,
178
+ "ņ": 176,
179
+ "ň": 177,
180
+ "ŋ": 178,
181
+ "Ō": 179,
182
+ "ō": 180,
183
+ "ŏ": 181,
184
+ "Ő": 182,
185
+ "ő": 183,
186
+ "Œ": 184,
187
+ "œ": 185,
188
+ "ŕ": 186,
189
+ "ŗ": 187,
190
+ "Ř": 188,
191
+ "ř": 189,
192
+ "Ś": 190,
193
+ "ś": 191,
194
+ "Ŝ": 192,
195
+ "ŝ": 193,
196
+ "Ş": 194,
197
+ "ş": 195,
198
+ "Š": 196,
199
+ "š": 197,
200
+ "Ţ": 198,
201
+ "ţ": 199,
202
+ "Ť": 200,
203
+ "ť": 201,
204
+ "Ŧ": 202,
205
+ "ũ": 203,
206
+ "Ū": 204,
207
+ "ū": 205,
208
+ "ŭ": 206,
209
+ "ů": 207,
210
+ "ű": 208,
211
+ "ų": 209,
212
+ "ŵ": 210,
213
+ "ŷ": 211,
214
+ "Ÿ": 212,
215
+ "Ź": 213,
216
+ "ź": 214,
217
+ "Ż": 215,
218
+ "ż": 216,
219
+ "Ž": 217,
220
+ "ž": 218,
221
+ "Ƅ": 219,
222
+ "Ƌ": 220,
223
+ "ƌ": 221,
224
+ "Ǝ": 222,
225
+ "Ə": 223,
226
+ "ƒ": 224,
227
+ "ơ": 225,
228
+ "ư": 226,
229
+ "ƿ": 227,
230
+ "ǁ": 228,
231
+ "ǂ": 229,
232
+ "ǃ": 230,
233
+ "ǎ": 231,
234
+ "ǐ": 232,
235
+ "ǒ": 233,
236
+ "ǔ": 234,
237
+ "ǚ": 235,
238
+ "ǝ": 236,
239
+ "ǣ": 237,
240
+ "Ǧ": 238,
241
+ "ǧ": 239,
242
+ "ǩ": 240,
243
+ "ǫ": 241,
244
+ "ǵ": 242,
245
+ "ǹ": 243,
246
+ "ȁ": 244,
247
+ "ȃ": 245,
248
+ "Ș": 246,
249
+ "ș": 247,
250
+ "Ț": 248,
251
+ "ț": 249,
252
+ "Ȝ": 250,
253
+ "ȝ": 251,
254
+ "ȧ": 252,
255
+ "Ɂ": 253,
256
+ "ɂ": 254,
257
+ "ɐ": 255,
258
+ "ɑ": 256,
259
+ "ɒ": 257,
260
+ "ɔ": 258,
261
+ "ɕ": 259,
262
+ "ɖ": 260,
263
+ "ɗ": 261,
264
+ "ɘ": 262,
265
+ "ə": 263,
266
+ "ɛ": 264,
267
+ "ɜ": 265,
268
+ "ɝ": 266,
269
+ "ɟ": 267,
270
+ "ɡ": 268,
271
+ "ɣ": 269,
272
+ "ɥ": 270,
273
+ "ɦ": 271,
274
+ "ɨ": 272,
275
+ "ɩ": 273,
276
+ "ɪ": 274,
277
+ "ɫ": 275,
278
+ "ɮ": 276,
279
+ "ɯ": 277,
280
+ "ɲ": 278,
281
+ "ɳ": 279,
282
+ "ɶ": 280,
283
+ "ɷ": 281,
284
+ "ɸ": 282,
285
+ "ɹ": 283,
286
+ "ɺ": 284,
287
+ "ɾ": 285,
288
+ "ʁ": 286,
289
+ "ʂ": 287,
290
+ "ʃ": 288,
291
+ "ʇ": 289,
292
+ "ʈ": 290,
293
+ "ʊ": 291,
294
+ "ʋ": 292,
295
+ "ʌ": 293,
296
+ "ʎ": 294,
297
+ "ʏ": 295,
298
+ "ʐ": 296,
299
+ "ʑ": 297,
300
+ "ʒ": 298,
301
+ "ʔ": 299,
302
+ "ʕ": 300,
303
+ "ʘ": 301,
304
+ "ʙ": 302,
305
+ "ʝ": 303,
306
+ "ʟ": 304,
307
+ "ʧ": 305,
308
+ "ʹ": 306,
309
+ "ʻ": 307,
310
+ "ʼ": 308,
311
+ "ʽ": 309,
312
+ "ʾ": 310,
313
+ "ʿ": 311,
314
+ "ˀ": 312,
315
+ "ˆ": 313,
316
+ "ˇ": 314,
317
+ "ˈ": 315,
318
+ "ˊ": 316,
319
+ "ˋ": 317,
320
+ "ˌ": 318,
321
+ "ː": 319,
322
+ "Α": 320,
323
+ "Β": 321,
324
+ "Ε": 322,
325
+ "Η": 323,
326
+ "Τ": 324,
327
+ "Υ": 325,
328
+ "ν": 326,
329
+ "ο": 327,
330
+ "Ј": 328,
331
+ "М": 329,
332
+ "а": 330,
333
+ "б": 331,
334
+ "й": 332,
335
+ "к": 333,
336
+ "о": 334,
337
+ "с": 335,
338
+ "у": 336,
339
+ "ш": 337,
340
+ "я": 338,
341
+ "ـ": 339,
342
+ "ආ": 340,
343
+ "ජ": 341,
344
+ "බ": 342,
345
+ "ය": 343,
346
+ "ව": 344,
347
+ "ḋ": 345,
348
+ "Ḍ": 346,
349
+ "ḍ": 347,
350
+ "ḏ": 348,
351
+ "ḗ": 349,
352
+ "Ḡ": 350,
353
+ "Ḥ": 351,
354
+ "ḥ": 352,
355
+ "Ḩ": 353,
356
+ "ḫ": 354,
357
+ "ḱ": 355,
358
+ "ḵ": 356,
359
+ "ḷ": 357,
360
+ "ḻ": 358,
361
+ "ḿ": 359,
362
+ "ṁ": 360,
363
+ "Ṃ": 361,
364
+ "ṃ": 362,
365
+ "ṅ": 363,
366
+ "ṇ": 364,
367
+ "ṉ": 365,
368
+ "ṓ": 366,
369
+ "ṗ": 367,
370
+ "ṙ": 368,
371
+ "ṛ": 369,
372
+ "ṟ": 370,
373
+ "Ṣ": 371,
374
+ "ṣ": 372,
375
+ "ṫ": 373,
376
+ "Ṭ": 374,
377
+ "ṭ": 375,
378
+ "Ṯ": 376,
379
+ "ṯ": 377,
380
+ "Ṳ": 378,
381
+ "ṹ": 379,
382
+ "ẏ": 380,
383
+ "Ẓ": 381,
384
+ "ẓ": 382,
385
+ "ẞ": 383,
386
+ "ạ": 384,
387
+ "ả": 385,
388
+ "ấ": 386,
389
+ "ầ": 387,
390
+ "ẩ": 388,
391
+ "ậ": 389,
392
+ "ắ": 390,
393
+ "ằ": 391,
394
+ "ẵ": 392,
395
+ "ặ": 393,
396
+ "Ẹ": 394,
397
+ "ẹ": 395,
398
+ "ẻ": 396,
399
+ "ẽ": 397,
400
+ "Ế": 398,
401
+ "ế": 399,
402
+ "ề": 400,
403
+ "ể": 401,
404
+ "ễ": 402,
405
+ "ệ": 403,
406
+ "ỉ": 404,
407
+ "ị": 405,
408
+ "Ọ": 406,
409
+ "ọ": 407,
410
+ "ỏ": 408,
411
+ "ố": 409,
412
+ "ồ": 410,
413
+ "ổ": 411,
414
+ "ỗ": 412,
415
+ "ộ": 413,
416
+ "ớ": 414,
417
+ "ờ": 415,
418
+ "ở": 416,
419
+ "ợ": 417,
420
+ "ụ": 418,
421
+ "ủ": 419,
422
+ "ứ": 420,
423
+ "ử": 421,
424
+ "ữ": 422,
425
+ "ự": 423,
426
+ "ỳ": 424,
427
+ "ỹ": 425,
428
+ "ⱡ": 426,
429
+ "ー": 427,
430
+ "Ꜧ": 428,
431
+ "ꜧ": 429,
432
+ "ꞌ": 430,
433
+ "ꞯ": 431,
434
+ "fl": 432,
435
+ "0": 433,
436
+ "1": 434,
437
+ "2": 435,
438
+ "3": 436,
439
+ "4": 437,
440
+ "5": 438,
441
+ "6": 439,
442
+ "7": 440,
443
+ "8": 441,
444
+ "9": 442,
445
+ "³": 443,
446
+ "¹": 444,
447
+ "١": 445,
448
+ "٢": 446,
449
+ "٤": 447,
450
+ "٥": 448,
451
+ "٦": 449,
452
+ "٧": 450,
453
+ "٨": 451,
454
+ "٩": 452,
455
+ "۰": 453,
456
+ "०": 454,
457
+ "१": 455,
458
+ "२": 456,
459
+ "३": 457,
460
+ "४": 458,
461
+ "५": 459,
462
+ "६": 460,
463
+ "७": 461,
464
+ "८": 462,
465
+ "९": 463,
466
+ "၀": 464,
467
+ "၁": 465,
468
+ "၂": 466,
469
+ "၃": 467,
470
+ "၄": 468,
471
+ "၅": 469,
472
+ "၆": 470,
473
+ "၇": 471,
474
+ "၈": 472,
475
+ "၉": 473,
476
+ "០": 474,
477
+ "១": 475,
478
+ "២": 476,
479
+ "៣": 477,
480
+ "៤": 478,
481
+ "៥": 479,
482
+ "៦": 480,
483
+ "៧": 481,
484
+ "៨": 482,
485
+ "៩": 483,
486
+ "\t": 484,
487
+ " ": 485,
488
+ "!": 486,
489
+ "\"": 487,
490
+ "#": 488,
491
+ "$": 489,
492
+ "%": 490,
493
+ "&": 491,
494
+ "'": 492,
495
+ "(": 493,
496
+ ")": 494,
497
+ "*": 495,
498
+ "+": 496,
499
+ ",": 497,
500
+ "-": 498,
501
+ ".": 499,
502
+ "/": 500,
503
+ ":": 501,
504
+ ";": 502,
505
+ "<": 503,
506
+ "=": 504,
507
+ ">": 505,
508
+ "?": 506,
509
+ "@": 507,
510
+ "[": 508,
511
+ "\\": 509,
512
+ "]": 510,
513
+ "^": 511,
514
+ "_": 512,
515
+ "`": 513,
516
+ "{": 514,
517
+ "|": 515,
518
+ "}": 516,
519
+ "~": 517,
520
+ "": 518,
521
+ "€": 519,
522
+ "": 520,
523
+ "‚": 521,
524
+ "ƒ": 522,
525
+ "ˆ": 523,
526
+ "‰": 524,
527
+ "Š": 525,
528
+ "‹": 526,
529
+ "Œ": 527,
530
+ "": 528,
531
+ "Ž": 529,
532
+ "": 530,
533
+ "": 531,
534
+ "’": 532,
535
+ "“": 533,
536
+ "”": 534,
537
+ "•": 535,
538
+ "–": 536,
539
+ "—": 537,
540
+ "˜": 538,
541
+ "™": 539,
542
+ "š": 540,
543
+ "œ": 541,
544
+ "": 542,
545
+ "ž": 543,
546
+ "¡": 544,
547
+ "¢": 545,
548
+ "£": 546,
549
+ "¤": 547,
550
+ "¥": 548,
551
+ "¦": 549,
552
+ "§": 550,
553
+ "¨": 551,
554
+ "©": 552,
555
+ "«": 553,
556
+ "¬": 554,
557
+ "­": 555,
558
+ "®": 556,
559
+ "°": 557,
560
+ "±": 558,
561
+ "´": 559,
562
+ "¶": 560,
563
+ "·": 561,
564
+ "»": 562,
565
+ "½": 563,
566
+ "¿": 564,
567
+ "×": 565,
568
+ "÷": 566,
569
+ "˥": 567,
570
+ "˦": 568,
571
+ "˧": 569,
572
+ "˩": 570,
573
+ "̶": 571,
574
+ "־": 572,
575
+ "״": 573,
576
+ "،": 574,
577
+ "؟": 575,
578
+ "۞": 576,
579
+ "।": 577,
580
+ "॥": 578,
581
+ "ා": 579,
582
+ "ු": 580,
583
+ "ේ": 581,
584
+ "ෝ": 582,
585
+ "་": 583,
586
+ "།": 584,
587
+ " ": 585,
588
+ "᚛": 586,
589
+ "᚜": 587,
590
+ "​": 588,
591
+ "‌": 589,
592
+ "‍": 590,
593
+ "‎": 591,
594
+ "‏": 592,
595
+ "‐": 593,
596
+ "–": 594,
597
+ "—": 595,
598
+ "―": 596,
599
+ "‖": 597,
600
+ "‘": 598,
601
+ "’": 599,
602
+ "‚": 600,
603
+ "“": 601,
604
+ "”": 602,
605
+ "„": 603,
606
+ "†": 604,
607
+ "‡": 605,
608
+ "•": 606,
609
+ "‬": 607,
610
+ "‭": 608,
611
+ "‰": 609,
612
+ "′": 610,
613
+ "※": 611,
614
+ "‿": 612,
615
+ "⁂": 613,
616
+ "⁄": 614,
617
+ "⁎": 615,
618
+ "⁠": 616,
619
+ "⁣": 617,
620
+ "₡": 618,
621
+ "₣": 619,
622
+ "₤": 620,
623
+ "₩": 621,
624
+ "€": 622,
625
+ "₱": 623,
626
+ "₵": 624,
627
+ "₹": 625,
628
+ "₿": 626,
629
+ "™": 627,
630
+ "↊": 628,
631
+ "↋": 629,
632
+ "←": 630,
633
+ "↑": 631,
634
+ "→": 632,
635
+ "↗": 633,
636
+ "↫": 634,
637
+ "∂": 635,
638
+ "∆": 636,
639
+ "∇": 637,
640
+ "∈": 638,
641
+ "∉": 639,
642
+ "−": 640,
643
+ "∗": 641,
644
+ "∘": 642,
645
+ "∙": 643,
646
+ "√": 644,
647
+ "∝": 645,
648
+ "∞": 646,
649
+ "∴": 647,
650
+ "∼": 648,
651
+ "≈": 649,
652
+ "≒": 650,
653
+ "≠": 651,
654
+ "≡": 652,
655
+ "≤": 653,
656
+ "≥": 654,
657
+ "⊙": 655,
658
+ "⋅": 656,
659
+ "⌈": 657,
660
+ "⌉": 658,
661
+ "⌊": 659,
662
+ "⌋": 660,
663
+ "─": 661,
664
+ "█": 662,
665
+ "▔": 663,
666
+ "▼": 664,
667
+ "◉": 665,
668
+ "◊": 666,
669
+ "○": 667,
670
+ "●": 668,
671
+ "☃": 669,
672
+ "★": 670,
673
+ "☆": 671,
674
+ "☉": 672,
675
+ "☐": 673,
676
+ "☚": 674,
677
+ "☛": 675,
678
+ "☣": 676,
679
+ "☭": 677,
680
+ "☯": 678,
681
+ "☺": 679,
682
+ "☻": 680,
683
+ "♄": 681,
684
+ "♑": 682,
685
+ "♒": 683,
686
+ "♠": 684,
687
+ "♡": 685,
688
+ "♣": 686,
689
+ "♥": 687,
690
+ "♦": 688,
691
+ "♪": 689,
692
+ "♫": 690,
693
+ "♭": 691,
694
+ "♮": 692,
695
+ "♯": 693,
696
+ "✅": 694,
697
+ "✙": 695,
698
+ "✚": 696,
699
+ "✡": 697,
700
+ "✿": 698,
701
+ "❌": 699,
702
+ "❤": 700,
703
+ "❦": 701,
704
+ "⟨": 702,
705
+ "⟩": 703,
706
+ "⬄": 704,
707
+ "⬱": 705,
708
+ "⿰": 706,
709
+ "⿱": 707,
710
+ "⿺": 708,
711
+ "、": 709,
712
+ "。": 710,
713
+ "〉": 711,
714
+ "《": 712,
715
+ "》": 713,
716
+ "「": 714,
717
+ "」": 715,
718
+ "『": 716,
719
+ "』": 717,
720
+ "〜": 718,
721
+ "・": 719,
722
+ "꞉": 720,
723
+ "": 721,
724
+ "": 722,
725
+ "": 723,
726
+ "": 724,
727
+ "!": 725,
728
+ "�": 726,
729
+ "𝄆": 727,
730
+ "𝄇": 728,
731
+ "🆖": 729,
732
+ "🏰": 730,
733
+ "🏴": 731,
734
+ "👫": 732,
735
+ "👽": 733,
736
+ "😊": 734,
737
+ "😝": 735,
738
+ "🜨": 736,
739
+ "󠁢": 737,
740
+ "󠁧": 738,
741
+ "󠁬": 739,
742
+ "󠁳": 740,
743
+ "󠁷": 741,
744
+ "󠁿": 742,
745
+ "􏿾": 743
746
+ }