Hugging Face's logo

Mohamed-Abbas
/
AR2EN

Transformers
Safetensors
encoder_decoder
Model card Files
xet
 Community
Mohamed-Abbas commited on
Commit
402eab1
·
verified ·
1 Parent(s): f53f4a3

Upload tokenizer

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +4 -35
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +9 -327
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,37 +1,6 @@
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
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,339 +1,21 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "+ا",
5
  "lstrip": false,
6
  "normalized": true,
7
  "rstrip": false,
8
- "single_word": true,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "+ك",
13
- "lstrip": false,
14
- "normalized": true,
15
- "rstrip": false,
16
- "single_word": true,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "ب+",
21
- "lstrip": false,
22
- "normalized": true,
23
- "rstrip": false,
24
- "single_word": true,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "+هم",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": true,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "+ات",
37
- "lstrip": false,
38
- "normalized": true,
39
- "rstrip": false,
40
- "single_word": true,
41
- "special": true
42
- },
43
- "5": {
44
- "content": "+ي",
45
- "lstrip": false,
46
- "normalized": true,
47
- "rstrip": false,
48
- "single_word": true,
49
- "special": true
50
- },
51
- "6": {
52
- "content": "ل+",
53
- "lstrip": false,
54
- "normalized": true,
55
- "rstrip": false,
56
- "single_word": true,
57
- "special": true
58
- },
59
- "7": {
60
- "content": "+هما",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": true,
65
- "special": true
66
- },
67
- "8": {
68
- "content": "+نا",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": true,
73
- "special": true
74
- },
75
- "9": {
76
- "content": "+ن",
77
- "lstrip": false,
78
- "normalized": true,
79
- "rstrip": false,
80
- "single_word": true,
81
- "special": true
82
- },
83
- "10": {
84
- "content": "+ها",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": true,
89
- "special": true
90
- },
91
- "11": {
92
- "content": "+كما",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": true,
97
- "special": true
98
- },
99
- "12": {
100
- "content": "+ة",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": true,
105
- "special": true
106
- },
107
- "13": {
108
- "content": "ف+",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": true,
113
- "special": true
114
- },
115
- "14": {
116
- "content": "+كم",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": true,
121
- "special": true
122
- },
123
- "15": {
124
- "content": "+كن",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": true,
129
- "special": true
130
- },
131
- "16": {
132
- "content": "+ت",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": true,
137
- "special": true
138
- },
139
- "17": {
140
- "content": "[بريد]",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": true,
145
- "special": true
146
- },
147
- "18": {
148
- "content": "[مستخدم]",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": true,
153
- "special": true
154
- },
155
- "19": {
156
- "content": "لل+",
157
- "lstrip": false,
158
- "normalized": true,
159
- "rstrip": false,
160
- "single_word": true,
161
- "special": true
162
- },
163
- "20": {
164
- "content": "ال+",
165
- "lstrip": false,
166
- "normalized": true,
167
- "rstrip": false,
168
- "single_word": true,
169
- "special": true
170
- },
171
- "21": {
172
- "content": "[رابط]",
173
- "lstrip": false,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": true,
177
- "special": true
178
- },
179
- "22": {
180
- "content": "س+",
181
- "lstrip": false,
182
- "normalized": true,
183
- "rstrip": false,
184
- "single_word": true,
185
- "special": true
186
- },
187
- "23": {
188
- "content": "+ان",
189
- "lstrip": false,
190
- "normalized": true,
191
- "rstrip": false,
192
- "single_word": true,
193
- "special": true
194
- },
195
- "24": {
196
- "content": "+وا",
197
- "lstrip": false,
198
- "normalized": true,
199
- "rstrip": false,
200
- "single_word": true,
201
- "special": true
202
- },
203
- "25": {
204
- "content": "+ه",
205
- "lstrip": false,
206
- "normalized": true,
207
- "rstrip": false,
208
- "single_word": true,
209
- "special": true
210
- },
211
- "26": {
212
- "content": "+ون",
213
- "lstrip": false,
214
- "normalized": true,
215
- "rstrip": false,
216
- "single_word": true,
217
- "special": true
218
- },
219
- "27": {
220
- "content": "+هن",
221
- "lstrip": false,
222
- "normalized": true,
223
- "rstrip": false,
224
- "single_word": true,
225
- "special": true
226
- },
227
- "28": {
228
- "content": "+ين",
229
- "lstrip": false,
230
- "normalized": true,
231
- "rstrip": false,
232
- "single_word": true,
233
- "special": true
234
- },
235
- "29": {
236
- "content": "و+",
237
- "lstrip": false,
238
- "normalized": true,
239
- "rstrip": false,
240
- "single_word": true,
241
- "special": true
242
- },
243
- "30": {
244
- "content": "ك+",
245
- "lstrip": false,
246
- "normalized": true,
247
- "rstrip": false,
248
- "single_word": true,
249
- "special": true
250
- },
251
- "31": {
252
- "content": "[PAD]",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "32": {
260
- "content": "[UNK]",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "33": {
268
- "content": "[CLS]",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "34": {
276
- "content": "[SEP]",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "35": {
284
- "content": "[MASK]",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
  "single_word": false,
289
  "special": true
290
  }
291
  },
 
292
  "clean_up_tokenization_spaces": false,
293
- "cls_token": "[CLS]",
294
- "do_basic_tokenize": true,
295
- "do_lower_case": false,
296
  "extra_special_tokens": {},
297
- "mask_token": "[MASK]",
298
- "max_len": 512,
299
- "model_max_length": 512,
300
- "never_split": [
301
- "+ك",
302
- "+كما",
303
- "ك+",
304
- "+وا",
305
- "+ين",
306
- "و+",
307
- "+كن",
308
- "+ان",
309
- "+هم",
310
- "+ة",
311
- "[بريد]",
312
- "لل+",
313
- "+ي",
314
- "+ت",
315
- "+ن",
316
- "س+",
317
- "ل+",
318
- "[مستخدم]",
319
- "+كم",
320
- "+ا",
321
- "ب+",
322
- "ف+",
323
- "+نا",
324
- "+ها",
325
- "+ون",
326
- "+هما",
327
- "ال+",
328
- "+ه",
329
- "+هن",
330
- "+ات",
331
- "[رابط]"
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
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": true,
8
  "rstrip": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
+ "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
 
 
16
  "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff