GeorgeIbrahim commited on
Commit
fb78010
โ€ข
1 Parent(s): 2e58c8c

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +339 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,339 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "124": {
4
+ "content": "+ุง",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": true,
9
+ "special": true
10
+ },
11
+ "125": {
12
+ "content": "+ุฉ",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": true,
17
+ "special": true
18
+ },
19
+ "126": {
20
+ "content": "+ุช",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": true,
25
+ "special": true
26
+ },
27
+ "127": {
28
+ "content": "+ูƒ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": true,
33
+ "special": true
34
+ },
35
+ "128": {
36
+ "content": "+ู†",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": true,
41
+ "special": true
42
+ },
43
+ "129": {
44
+ "content": "+ู‡",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": true,
49
+ "special": true
50
+ },
51
+ "130": {
52
+ "content": "+ูŠ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": true,
57
+ "special": true
58
+ },
59
+ "448": {
60
+ "content": "ุจ+",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": true,
65
+ "special": true
66
+ },
67
+ "635": {
68
+ "content": "ุณ+",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": true,
73
+ "special": true
74
+ },
75
+ "765": {
76
+ "content": "ู+",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": true,
81
+ "special": true
82
+ },
83
+ "802": {
84
+ "content": "ูƒ+",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": true,
89
+ "special": true
90
+ },
91
+ "816": {
92
+ "content": "ู„+",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": true,
97
+ "special": true
98
+ },
99
+ "897": {
100
+ "content": "ูˆ+",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": true,
105
+ "special": true
106
+ },
107
+ "1012": {
108
+ "content": "+ุงุช",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": true,
113
+ "special": true
114
+ },
115
+ "1013": {
116
+ "content": "+ุงู†",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": true,
121
+ "special": true
122
+ },
123
+ "1015": {
124
+ "content": "+ูƒู…",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": true,
129
+ "special": true
130
+ },
131
+ "1016": {
132
+ "content": "+ูƒู†",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": true,
137
+ "special": true
138
+ },
139
+ "1017": {
140
+ "content": "+ู†ุง",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": true,
145
+ "special": true
146
+ },
147
+ "1018": {
148
+ "content": "+ู‡ุง",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": true,
153
+ "special": true
154
+ },
155
+ "1019": {
156
+ "content": "+ู‡ู…",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": true,
161
+ "special": true
162
+ },
163
+ "1020": {
164
+ "content": "+ู‡ู†",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": true,
169
+ "special": true
170
+ },
171
+ "1021": {
172
+ "content": "+ูˆุง",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": true,
177
+ "special": true
178
+ },
179
+ "1022": {
180
+ "content": "+ูˆู†",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": true,
185
+ "special": true
186
+ },
187
+ "1023": {
188
+ "content": "+ูŠู†",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": true,
193
+ "special": true
194
+ },
195
+ "3000": {
196
+ "content": "ุงู„+",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": true,
201
+ "special": true
202
+ },
203
+ "6154": {
204
+ "content": "ู„ู„+",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": true,
209
+ "special": true
210
+ },
211
+ "8270": {
212
+ "content": "+ูƒู…ุง",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": true,
217
+ "special": true
218
+ },
219
+ "8271": {
220
+ "content": "+ู‡ู…ุง",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": true,
225
+ "special": true
226
+ },
227
+ "29756": {
228
+ "content": "[CLS]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "29757": {
236
+ "content": "[PAD]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "29758": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "29759": {
252
+ "content": "[UNK]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "46585": {
260
+ "content": "[MASK]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "46586": {
268
+ "content": "[ุจุฑูŠุฏ]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": true,
273
+ "special": true
274
+ },
275
+ "46587": {
276
+ "content": "[ุฑุงุจุท]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": true,
281
+ "special": true
282
+ },
283
+ "57701": {
284
+ "content": "[ู…ุณุชุฎุฏู…]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": true,
289
+ "special": true
290
+ }
291
+ },
292
+ "clean_up_tokenization_spaces": true,
293
+ "cls_token": "[CLS]",
294
+ "do_basic_tokenize": true,
295
+ "do_lower_case": false,
296
+ "full_tokenizer_file": null,
297
+ "mask_token": "[MASK]",
298
+ "max_len": 512,
299
+ "model_max_length": 512,
300
+ "never_split": [
301
+ "+ูˆุง",
302
+ "ุณ+",
303
+ "[ู…ุณุชุฎุฏู…]",
304
+ "+ูƒ",
305
+ "+ู‡ู…",
306
+ "+ุฉ",
307
+ "+ู†",
308
+ "ู„ู„+",
309
+ "[ุจุฑูŠุฏ]",
310
+ "[ุฑุงุจุท]",
311
+ "+ู‡",
312
+ "+ูƒู†",
313
+ "+ุง",
314
+ "+ุงุช",
315
+ "+ูŠ",
316
+ "ุจ+",
317
+ "+ู†ุง",
318
+ "+ู‡ู†",
319
+ "+ูƒู…",
320
+ "ูƒ+",
321
+ "+ูŠู†",
322
+ "+ู‡ู…ุง",
323
+ "ูˆ+",
324
+ "+ูƒู…ุง",
325
+ "+ุงู†",
326
+ "+ุช",
327
+ "+ูˆู†",
328
+ "ู„+",
329
+ "+ู‡ุง",
330
+ "ุงู„+",
331
+ "ู+"
332
+ ],
333
+ "pad_token": "[PAD]",
334
+ "sep_token": "[SEP]",
335
+ "strip_accents": null,
336
+ "tokenize_chinese_chars": true,
337
+ "tokenizer_class": "BertTokenizer",
338
+ "unk_token": "[UNK]"
339
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff