gsaltintas commited on
Commit
196375b
·
verified ·
1 Parent(s): 1805e8b

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +5 -1
  2. special_tokens_map.json +0 -4
  3. tokenizer.json +29 -47
  4. tokenizer_config.json +0 -20
  5. vocab.json +314 -314
README.md CHANGED
@@ -47,4 +47,8 @@ tokens = tokenizer.encode("Hello, world!")
47
  ## Sample Encoding
48
  | Text | Tokens | Token IDs |
49
  |------|--------|-----------|
50
- | `yirmi iki+dokuz=otuz bir\ntwenty two+nine=thirty one` | `y, i, r, m, i, Ġ, i, k, i, +, d, o, k, u, z, =, o, t, u, z` | `91, 75, 84, 79, 75, 223, 75, 77, 75, 3, 70, 81, 77, 87, 92, 4, 81, 86, 87, 92` |
 
 
 
 
 
47
  ## Sample Encoding
48
  | Text | Tokens | Token IDs |
49
  |------|--------|-----------|
50
+ | `yirmi iki+dokuz=otuz bir\ntwenty two+nine=thirty one` | `y, i, r, m, i, Ġ, i, k, i, +, d, o, k, u, z, =, o, t, u, z` | `91, 75, 84, 79, 75, 223, 75, 77, 75, 13, 70, 81, 77, 87, 92, 31, 81, 86, 87, 92` |
51
+
52
+ Command used to create this tokenizer:
53
+ ```bash
54
+ ['/home/gsa/tokenizers2/flexitok/tokenizer_training/train_tokenizers.py', 'algorithm=bpe', 'vocab_size=2000', 'langs=[arb_Arab]', 'data_dir=/scratch/gsa/data/multilingual-addition/', 'output_dir=/scratch/gsa/trained_tokenizers/multilingual_addition', 'pretokenizer=custom:addition', 'number_handling=ltr_3digit', 'add_numbers=false', 'handle_contractions=false', 'unicode_normalization=nfc', 'use_byte_level_regex=false', 'byte_fallback=false', 'strip_zero_width=false', 'cjk_char_split=false', 'add_cjk_chars=false', 'max_lines=-1', 'test_string=yirmi iki+dokuz=otuz bir\\ntwenty two+nine=thirty one', 'hf.publish_to_hf=true', 'hf_repo_prefix=flexitok/', 'hf.hf_repo_id=flexitok/maddition_arb_Arab_2000', 'hf.collections=[flexitok/multilingual_addition_tokenizers]']
special_tokens_map.json CHANGED
@@ -1,8 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "+",
4
- "="
5
- ],
6
  "bos_token": "<s>",
7
  "eos_token": "</s>",
8
  "pad_token": "<pad>"
 
1
  {
 
 
 
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>"
tokenizer.json CHANGED
@@ -29,24 +29,6 @@
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
- },
33
- {
34
- "id": 3,
35
- "content": "+",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": false,
40
- "special": true
41
- },
42
- {
43
- "id": 4,
44
- "content": "=",
45
- "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
- "normalized": false,
49
- "special": true
50
  }
51
  ],
52
  "normalizer": {
@@ -99,35 +81,35 @@
99
  "<s>": 0,
100
  "</s>": 1,
101
  "<pad>": 2,
102
- "+": 3,
103
- "=": 4,
104
- "!": 5,
105
- "\"": 6,
106
- "#": 7,
107
- "$": 8,
108
- "%": 9,
109
- "&": 10,
110
- "'": 11,
111
- "(": 12,
112
- ")": 13,
113
- "*": 14,
114
- ",": 15,
115
- "-": 16,
116
- ".": 17,
117
- "/": 18,
118
- "0": 19,
119
- "1": 20,
120
- "2": 21,
121
- "3": 22,
122
- "4": 23,
123
- "5": 24,
124
- "6": 25,
125
- "7": 26,
126
- "8": 27,
127
- "9": 28,
128
- ":": 29,
129
- ";": 30,
130
- "<": 31,
131
  ">": 32,
132
  "?": 33,
133
  "@": 34,
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
 
81
  "<s>": 0,
82
  "</s>": 1,
83
  "<pad>": 2,
84
+ "!": 3,
85
+ "\"": 4,
86
+ "#": 5,
87
+ "$": 6,
88
+ "%": 7,
89
+ "&": 8,
90
+ "'": 9,
91
+ "(": 10,
92
+ ")": 11,
93
+ "*": 12,
94
+ "+": 13,
95
+ ",": 14,
96
+ "-": 15,
97
+ ".": 16,
98
+ "/": 17,
99
+ "0": 18,
100
+ "1": 19,
101
+ "2": 20,
102
+ "3": 21,
103
+ "4": 22,
104
+ "5": 23,
105
+ "6": 24,
106
+ "7": 25,
107
+ "8": 26,
108
+ "9": 27,
109
+ ":": 28,
110
+ ";": 29,
111
+ "<": 30,
112
+ "=": 31,
113
  ">": 32,
114
  "?": 33,
115
  "@": 34,
tokenizer_config.json CHANGED
@@ -23,28 +23,8 @@
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
- },
27
- "3": {
28
- "content": "+",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "=",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
  }
43
  },
44
- "additional_special_tokens": [
45
- "+",
46
- "="
47
- ],
48
  "bos_token": "<s>",
49
  "clean_up_tokenization_spaces": false,
50
  "eos_token": "</s>",
 
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  },
 
 
 
 
28
  "bos_token": "<s>",
29
  "clean_up_tokenization_spaces": false,
30
  "eos_token": "</s>",
vocab.json CHANGED
@@ -1,343 +1,343 @@
1
  {
2
- "ă": 194,
3
- "þ": 189,
4
- "Ü": 155,
5
- "ė": 214,
6
- "سبعÙĪÙĨ": 310,
7
- "عشر": 295,
8
- "اØ": 264,
9
- "Ď": 205,
10
- "أربعة": 318,
11
- "x": 90,
12
- "¿": 126,
13
- "L": 46,
14
- "Ø«ÙĦاثÙħائة": 326,
15
- "د": 300,
16
- "Á": 128,
17
  "ÙĪØ§Ø": 330,
18
- "J": 44,
19
- "ŃØ¯": 303,
20
- "Ĺ": 248,
21
- "ت": 271,
22
- "¾": 125,
23
- "b": 68,
24
- ">": 32,
25
- "P": 50,
26
- "&": 10,
27
- "à": 159,
28
- "č": 204,
29
- "ئت": 301,
30
- "-": 16,
31
- "©": 105,
32
- "§": 103,
33
- "Ċ": 201,
34
- ";": 30,
35
- "Ĵ": 243,
36
- "صÙģ": 339,
37
- "ġ": 224,
38
- "ì": 171,
39
- "^": 64,
40
- "Ø«ÙĦ": 287,
41
- "Ùħئتا": 337,
42
  "Ý": 156,
43
- "ĩ": 232,
44
- "ستÙĪÙĨ": 307,
45
- «ÙħاÙĨÙħائة": 316,
46
- "ĕ": 212,
47
- "Ø®ÙħسÙĪÙĨ": 322,
48
  "Ùħ": 262,
49
- "Ā": 191,
50
- "Ø®Ùħس": 291,
51
- "j": 76,
52
- "Ð": 143,
53
- "Ě": 217,
54
- "²": 113,
55
- "\"": 6,
56
- £Ø±Ø¨Ø¹ÙĪÙĨ": 319,
57
- "À": 127,
58
- "Ą": 195,
59
- ",": 15,
60
- "عشرÙĪÙĨ": 327,
61
- "Ã": 130,
62
- "B": 36,
63
- "اث": 279,
64
  "o": 81,
65
- "Ń": 258,
66
- "'": 11,
67
- "Ø«ÙħاÙĨÙĬ": 317,
68
- "r": 84,
69
- "=": 4,
70
- "ī": 234,
71
- "ü": 187,
72
- "¨": 104,
73
- "|": 94,
74
- "Ĭ": 235,
75
- "ربع": 289,
76
- "C": 37,
77
- ")": 13,
78
- "+": 3,
79
- "Ģ": 225,
80
  "ÙħاÙĨ": 282,
81
- "6": 25,
82
- "Ê": 137,
83
- "Ùħئت": 304,
84
- "w": 89,
85
- "y": 91,
86
- ":": 29,
87
- "á": 160,
88
- "اÙĨ": 276,
89
- "</s>": 1,
90
- "1": 20,
91
- "¥": 101,
92
- "Ę": 215,
93
- "Ø«ÙħاÙĨÙĪÙĨ": 315,
94
- "سبعة": 309,
95
- "Ĕ": 211,
96
- "æ": 165,
97
- "3": 22,
98
- "Ç": 134,
99
- "¬": 108,
100
- "Q": 51,
101
- "ę": 216,
102
- "É": 136,
103
- "W": 57,
104
- "2": 21,
105
- "ą": 196,
106
- "k": 77,
107
- "µ": 116,
108
- "â": 161,
109
- "Ħ": 229,
110
- "ÙħئتاÙĨ": 329,
111
- "<pad>": 2,
112
- "Ø«ÙĦاثÙĪÙĨ": 325,
113
  "Ñ": 144,
114
- "ñ": 176,
115
- "سع": 283,
116
- "ÙĪÙĨ": 268,
117
- "İ": 239,
118
- "(": 12,
119
- "¯": 110,
120
- "ĵ": 244,
121
- "س": 265,
122
- "/": 18,
123
- "{": 93,
124
- "Û": 154,
125
- "Ø«": 273,
126
- "Í": 140,
127
- "´Ø±": 293,
128
- "Ė": 213,
129
- "ĝ": 220,
130
- "أربعÙħائة": 320,
131
- "Î": 141,
132
- "v": 88,
133
- "·": 118,
134
- "U": 55,
135
- "سبع": 285,
136
- "<": 31,
137
  "H": 42,
138
- "ست": 284,
139
- "9": 28,
140
- "Ł": 256,
141
- "Ĩ": 231,
142
- "Đ": 207,
143
- "e": 71,
144
- "z": 92,
145
- "ļ": 251,
146
  "ij": 242,
147
- "O": 49,
148
- "I": 43,
149
- "Ø«ÙħاÙĨÙĬØ©": 328,
150
- "]": 63,
151
- "شر": 294,
152
- "Õ": 148,
 
 
153
  "Ùħائة": 270,
154
- "´": 115,
155
- "f": 72,
156
- "ر": 275,
157
- "é": 168,
158
- "l": 78,
159
- "%": 9,
160
- "p": 82,
161
- "F": 40,
162
- "¤": 100,
163
- "å": 164,
164
- "E": 39,
165
- "®": 109,
166
- "ØŃد": 333,
167
- "\\": 62,
168
- "K": 45,
169
- "8": 27,
 
 
 
 
 
 
 
170
  "Æ": 133,
171
- "ع": 266,
172
- "î": 173,
173
- "Ø©": 261,
 
 
 
 
 
 
 
 
174
  "į": 238,
175
- "h": 74,
176
- "اثÙĨاÙĨ": 331,
177
- "!": 5,
178
- "ç": 166,
179
- "»": 122,
180
- "¦": 102,
181
- "m": 79,
182
- "ı": 240,
183
- "ŀ": 255,
184
- "ľ": 253,
185
- "¼": 123,
186
- "ë": 170,
187
- "£": 99,
188
- "¡": 97,
189
- "Ø®Ùħ": 281,
190
- "Ġ": 223,
191
- "ÙĨ": 263,
192
  "V": 56,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
193
  "تسعÙħائة": 314,
194
- "n": 80,
195
- "ß": 158,
196
- "ø": 183,
197
  "ô": 179,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
198
  "Ø®Ùħسة": 321,
199
- "G": 41,
200
- "*": 14,
201
- "µÙģ": 338,
202
- "ê": 169,
203
- "ÙĪØ§ØŃد": 332,
204
- "¹": 120,
205
- "7": 26,
206
- "ا": 260,
207
  "Ć": 197,
208
- "ď": 206,
209
- "s": 85,
210
- "®Ùħ": 280,
211
- "Ø£ÙĦ": 297,
212
- "#": 7,
 
 
 
 
 
 
 
 
 
 
 
 
213
  "Ù": 152,
214
- "q": 83,
215
- "ķ": 246,
216
- "c": 69,
217
- "Ķ": 245,
218
- "ĭ": 236,
219
- "½": 124,
 
 
 
220
  "تسع": 286,
221
- "ÿ": 190,
222
- "N": 48,
223
- "Ë": 138,
224
- "M": 47,
225
- "ā": 192,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
226
  "ã": 162,
227
  "¸": 119,
228
- "ä": 163,
229
- "đ": 208,
230
- "û": 186,
231
- "¦Øª": 299,
232
- "?": 33,
233
- "g": 73,
234
- "اثÙĨ": 305,
235
- "ł": 257,
236
- "T": 54,
237
- "4": 23,
238
- "أربع": 290,
239
- "Ô": 147,
240
- "Ă": 193,
241
  "Ø": 151,
242
- "Þ": 157,
243
- "Ø£ØŃد": 334,
244
- «ÙħاÙĨ": 288,
245
- "í": 172,
246
- "Â": 129,
247
- "ć": 198,
248
- "Ö": 149,
249
  "ó": 178,
250
- "ستة": 306,
251
- µÙ쨱": 340,
252
- "ÙħاØ": 269,
253
- "×": 150,
254
- "عشرة": 335,
255
- "Ŀ": 254,
256
- "_": 65,
257
- "è": 167,
258
- "ý": 188,
259
- "÷": 182,
260
- "Ľ": 252,
261
- "": 117,
262
  "Ó": 146,
263
- "¨Ø¹": 272,
264
- "Ä": 131,
265
- "ù": 184,
266
- "ğ": 222,
 
 
 
 
 
 
 
267
  "Ĉ": 199,
268
- "ÙĦ": 278,
269
- "Ò": 145,
270
- "Ø®ÙħسÙħائة": 323,
271
- "0": 19,
272
- "Ļ": 250,
273
- "`": 66,
274
- "Y": 59,
275
- "ï": 174,
276
- "اثÙĨا": 336,
277
- "«": 107,
278
- "ĉ": 200,
279
- "}": 95,
280
  "Ĝ": 219,
 
 
 
 
 
 
 
 
 
 
 
 
281
  "Č": 203,
282
- "ĺ": 249,
283
- ".": 17,
284
- "S": 53,
285
- "ĸ": 247,
286
- "³": 114,
287
- "ÙĪ": 259,
288
- "Ï": 142,
289
- "Ø£ÙĦÙģ": 298,
290
- "ª": 106,
291
- "ě": 218,
292
- "Ē": 209,
293
- "بع": 274,
294
- "ĥ": 228,
295
- "º": 121,
296
- "ú": 185,
297
- "<s>": 0,
298
- "õ": 180,
299
- "Ø«ÙĦاثة": 324,
300
- "t": 86,
301
- "ð": 175,
302
- "°": 111,
303
- "Ĥ": 227,
304
- "±": 112,
305
- "u": 87,
306
- "D": 38,
307
  "Ī": 233,
308
- "ò": 177,
309
- "Å": 132,
310
- "Ùģ": 296,
311
- "Ø£": 277,
312
- "i": 75,
313
- "[": 61,
314
- "تسعة": 312,
315
- "ċ": 202,
316
- "Ø«ÙĦاث": 292,
317
- "a": 67,
318
- "~": 96,
319
- "Į": 237,
320
- "A": 35,
321
- "@": 34,
322
- "X": 58,
323
- "ö": 181,
324
- "ģ": 226,
325
- "سبعÙħائة": 311,
326
- "$": 8,
327
- "ستÙħائة": 308,
328
- "¦Ø©": 267,
329
- "Ú": 153,
330
- "Ğ": 221,
331
- "IJ": 241,
332
- "5": 24,
333
- "ħ": 230,
334
- "Ì": 139,
335
- "d": 70,
336
- "ÙĬ": 302,
337
- "ē": 210,
338
- "تسعÙĪÙĨ": 313,
339
- "R": 52,
340
- "È": 135,
341
- "¢": 98,
342
- "Z": 60
343
  }
 
1
  {
2
+ "Ø£": 277,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "ÙĪØ§Ø": 330,
4
+ "«": 107,
5
+ "İ": 239,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "Ý": 156,
7
+ "*": 12,
8
+ "å": 164,
9
+ "ئت": 301,
10
+ "`": 66,
11
+ "¢": 98,
12
  "Ùħ": 262,
13
+ "ÙĨ": 263,
14
+ "ø": 183,
15
+ "O": 49,
16
+ "ستÙĪÙĨ": 307,
17
+ "³": 114,
18
+ "=": 31,
19
+ "Ùħئت": 304,
20
+ §": 260,
21
+ "ستة": 306,
 
 
 
 
 
 
22
  "o": 81,
23
+ "Y": 59,
24
+ "j": 76,
25
+ "ľ": 253,
26
+ "ò": 177,
27
+ "Ùģ": 296,
 
 
 
 
 
 
 
 
 
 
28
  "ÙħاÙĨ": 282,
29
+ "اثÙĨاÙĨ": 331,
30
+ "c": 69,
31
+ "ĭ": 236,
32
+ "1": 19,
33
+ "سبعÙħائة": 311,
34
+ "Ô": 147,
35
+ "f": 72,
36
+ "M": 47,
37
+ "¤": 100,
38
+ "t": 86,
39
+ "ĉ": 200,
40
+ "I": 43,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  "Ñ": 144,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  "H": 42,
43
+ "đ": 208,
44
+ "Þ": 157,
45
+ "#": 5,
46
+ "È": 135,
 
 
 
 
47
  "ij": 242,
48
+ "§": 103,
49
+ "Ģ": 225,
50
+ "Ë": 138,
51
+ "ă": 194,
52
+ "¨": 104,
53
+ "á": 160,
54
+ "ċ": 202,
55
+ "ÙħاØ": 269,
56
  "Ùħائة": 270,
57
+ "®Ùħ": 280,
58
+ "à": 159,
59
+ "ß": 158,
60
+ "عشر": 295,
61
+ "č": 204,
62
+ "ı": 240,
63
+ "h": 74,
64
+ "T": 54,
65
+ "X": 58,
66
+ "½": 124,
67
+ "Ď": 205,
68
+ "6": 24,
69
+ "شر": 294,
70
+ "v": 88,
71
+ "ست": 284,
72
+ "ļ": 251,
73
+ "ÙĦ": 278,
74
+ "¶": 117,
75
+ "?": 33,
76
+ "Ĭ": 235,
77
+ "4": 22,
78
+ ":": 28,
79
+ "$": 6,
80
  "Æ": 133,
81
+ "w": 89,
82
+ "Ø«ÙĦ": 287,
83
+ "n": 80,
84
+ "Ï": 142,
85
+ "+": 13,
86
+ "ĺ": 249,
87
+ "_": 65,
88
+ "r": 84,
89
+ "اثÙĨ": 305,
90
+ "¹": 120,
91
+ "Ø«ÙĦاثة": 324,
92
  "į": 238,
93
+ "Ā": 191,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
94
  "V": 56,
95
+ "ě": 218,
96
+ "ķ": 246,
97
+ "Ġ": 223,
98
+ "ĸ": 247,
99
+ "<pad>": 2,
100
+ "0": 18,
101
+ "Ą": 195,
102
+ "سبع": 285,
103
+ "ĝ": 220,
104
+ "Ò": 145,
105
+ "i": 75,
106
+ "ē": 210,
107
+ "ğ": 222,
108
+ ",": 14,
109
+ "Ä": 131,
110
+ "°": 111,
111
+ "þ": 189,
112
+ "Ø®Ùħس": 291,
113
+ "ç": 166,
114
+ "Q": 51,
115
+ "´": 115,
116
+ "9": 27,
117
+ "5": 23,
118
+ "]": 63,
119
+ "¨Ø¹": 272,
120
+ "Ì": 139,
121
+ "b": 68,
122
+ "s": 85,
123
+ "Ê": 137,
124
+ "¯": 110,
125
+ "ربع": 289,
126
+ "z": 92,
127
+ "</s>": 1,
128
+ "Ļ": 250,
129
+ "ï": 174,
130
+ "Į": 237,
131
+ "U": 55,
132
+ "N": 48,
133
+ "ġ": 224,
134
+ "C": 37,
135
+ "Ø«": 273,
136
+ "P": 50,
137
+ "Ø«ÙĦاثÙħائة": 326,
138
  "تسعÙħائة": 314,
139
+ "ر": 275,
 
 
140
  "ô": 179,
141
+ "±": 112,
142
+ "¦": 102,
143
+ "~": 96,
144
+ "ł": 257,
145
+ "©": 105,
146
+ ">": 32,
147
+ "ħ": 230,
148
+ "أربعÙħائة": 320,
149
+ "Í": 140,
150
+ "ù": 184,
151
+ "K": 45,
152
+ "ĵ": 244,
153
+ "Ã": 130,
154
+ "õ": 180,
155
+ "u": 87,
156
+ "Ľ": 252,
157
+ "Ŀ": 254,
158
+ ")": 11,
159
+ "m": 79,
160
+ "ć": 198,
161
+ "a": 67,
162
+ "A": 35,
163
+ "¿": 126,
164
+ "G": 41,
165
+ "R": 52,
166
+ "û": 186,
167
+ "ģ": 226,
168
+ "Ü": 155,
169
+ "B": 36,
170
+ "{": 93,
171
+ "أربعة": 318,
172
+ "ª": 106,
173
+ "اثÙĨا": 336,
174
+ "x": 90,
175
+ "Đ": 207,
176
+ "Ħ": 229,
177
+ "Å": 132,
178
+ "æ": 165,
179
+ "عشرÙĪÙĨ": 327,
180
+ "î": 173,
181
+ "É": 136,
182
+ "W": 57,
183
+ "D": 38,
184
+ "¥": 101,
185
+ "Ø«ÙĦاث": 292,
186
+ "Ė": 213,
187
+ "ë": 170,
188
+ "Ð": 143,
189
+ "ÙĪ": 259,
190
+ "[": 61,
191
  "Ø®Ùħسة": 321,
192
+ "è": 167,
193
+ "Ç": 134,
194
+ "IJ": 241,
195
+ "ĩ": 232,
 
 
 
 
196
  "Ć": 197,
197
+ "í": 172,
198
+ "\"": 4,
199
+ "¾": 125,
200
+ "Ń": 258,
201
+ "ع": 266,
202
+ "|": 94,
203
+ "ñ": 176,
204
+ "(": 10,
205
+ "Ø«ÙħاÙĨ": 288,
206
+ "Ē": 209,
207
+ "l": 78,
208
+ "Ĥ": 227,
209
+ "e": 71,
210
+ "تسعÙĪÙĨ": 313,
211
+ "ÙħئتاÙĨ": 329,
212
+ "ŀ": 255,
213
+ "÷": 182,
214
  "Ù": 152,
215
+ "¬": 108,
216
+ "Ø£ÙĦÙģ": 298,
217
+ "اث": 279,
218
+ "ŃØ¯": 303,
219
+ "E": 39,
220
+ "ä": 163,
221
+ "Ø«ÙħاÙĨÙħائة": 316,
222
+ "تسعة": 312,
223
+ "ت": 271,
224
  "تسع": 286,
225
+ "k": 77,
226
+ "y": 91,
227
+ "سبعÙĪÙĨ": 310,
228
+ "سبعة": 309,
229
+ "<": 30,
230
+ "¦Ø©": 267,
231
+ "²": 113,
232
+ "Ķ": 245,
233
+ "ÙĬ": 302,
234
+ "p": 82,
235
+ "س": 265,
236
+ "ö": 181,
237
+ "'": 9,
238
+ "»": 122,
239
+ "-": 15,
240
+ "Ł": 256,
241
+ "Á": 128,
242
+ "2": 20,
243
+ "é": 168,
244
+ "ą": 196,
245
+ "L": 46,
246
+ "Ø«ÙħاÙĨÙĬ": 317,
247
+ ";": 29,
248
+ "S": 53,
249
+ "Â": 129,
250
+ "µÙģ": 338,
251
+ "J": 44,
252
+ "ú": 185,
253
+ "¦Øª": 299,
254
+ "\\": 62,
255
+ "F": 40,
256
+ "Ğ": 221,
257
+ "Î": 141,
258
+ "3": 21,
259
+ "×": 150,
260
+ "Ø®Ùħ": 281,
261
+ "ستÙħائة": 308,
262
+ "Ø«ÙħاÙĨÙĬØ©": 328,
263
+ "سع": 283,
264
+ "عشرة": 335,
265
+ "Õ": 148,
266
+ "d": 70,
267
+ "ĥ": 228,
268
+ "<s>": 0,
269
  "ã": 162,
270
  "¸": 119,
271
+ "Ùħئتا": 337,
272
+ "أربعÙĪÙĨ": 319,
273
+ "¼": 123,
274
+ "ÙĪØ§ØŃد": 332,
275
+ "Ú": 153,
 
 
 
 
 
 
 
 
276
  "Ø": 151,
277
+ "Ċ": 201,
278
+ "Ĺ": 248,
279
+ ®ÙħسÙħائة": 323,
280
+ "g": 73,
 
 
 
281
  "ó": 178,
282
+ "Ö": 149,
283
+ ¯": 300,
284
+ ®ÙħسÙĪÙĨ": 322,
285
+ "Ø£ÙĦ": 297,
286
+ "%": 7,
287
+ "Ø«ÙĦاثÙĪÙĨ": 325,
288
+ "&": 8,
289
+ "ØŃد": 333,
290
+ "Ĩ": 231,
291
+ "Z": 60,
292
+ "بع": 274,
293
+ "7": 25,
294
  "Ó": 146,
295
+ "Ă": 193,
296
+ "صÙ쨱": 340,
297
+ "À": 127,
298
+ "^": 64,
299
+ "ā": 192,
300
+ "ð": 175,
301
+ "!": 3,
302
+ "ĕ": 212,
303
+ "Ø©": 261,
304
+ "®": 109,
305
+ "Ĵ": 243,
306
  "Ĉ": 199,
307
+ "@": 34,
308
+ "º": 121,
309
+ ".": 16,
310
+ "ì": 171,
311
+ "ÙĪÙĨ": 268,
 
 
 
 
 
 
 
312
  "Ĝ": 219,
313
+ "´Ø±": 293,
314
+ "·": 118,
315
+ "صÙģ": 339,
316
+ "8": 26,
317
+ "£": 99,
318
+ "ÿ": 190,
319
+ "Ø£ØŃد": 334,
320
+ "ü": 187,
321
+ "¡": 97,
322
+ "}": 95,
323
+ "â": 161,
324
+ "ď": 206,
325
  "Č": 203,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
326
  "Ī": 233,
327
+ "Ĕ": 211,
328
+ "ý": 188,
329
+ "q": 83,
330
+ "ė": 214,
331
+ "µ": 116,
332
+ "Ě": 217,
333
+ "ê": 169,
334
+ "Û": 154,
335
+ "ī": 234,
336
+ "ę": 216,
337
+ "/": 17,
338
+ "Ę": 215,
339
+ "أربع": 290,
340
+ "اØ": 264,
341
+ "اÙĨ": 276,
342
+ "Ø«ÙħاÙĨÙĪÙĨ": 315
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
343
  }