Hugging Face's logo

muratsimsek003
/
turkish-loodos-bert-base-uncased-qa

Question Answering
Transformers
Safetensors
albert
Inference Endpoints
Model card Files Community
muratsimsek003 commited on
Commit
6aa7ba9
•
1 Parent(s): 4eb8d39

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +17 -3
  2. spiece.model +3 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +204 -11
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "cls_token": {
3
  "content": "[CLS]",
4
  "lstrip": false,
@@ -6,15 +13,22 @@
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,
@@ -28,7 +42,7 @@
28
  "single_word": false
29
  },
30
  "unk_token": {
31
- "content": "[UNK]",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
1
  {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
  "cls_token": {
10
  "content": "[CLS]",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "mask_token": {
24
  "content": "[MASK]",
25
+ "lstrip": true,
26
  "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
+ "content": "<pad>",
32
  "lstrip": false,
33
  "normalized": false,
34
  "rstrip": false,
 
42
  "single_word": false
43
  },
44
  "unk_token": {
45
+ "content": "<unk>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0906192fc8a73500782d11318813c4554fb0aeeb2ded6899b69839f09958ee99
3
+ size 862541
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "[PAD]",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,7 +9,7 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
@@ -34,24 +34,217 @@
34
  },
35
  "4": {
36
  "content": "[MASK]",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
- "clean_up_tokenization_spaces": true,
 
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
  "do_lower_case": false,
 
 
48
  "mask_token": "[MASK]",
49
  "model_max_length": 512,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
57
  }
 
1
  {
2
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
 
9
  "special": true
10
  },
11
  "1": {
12
+ "content": "<unk>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
 
34
  },
35
  "4": {
36
  "content": "[MASK]",
37
+ "lstrip": true,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "5": {
44
+ "content": "(",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": ")",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "”",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "\"",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "-",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": ".",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "–",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "!",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": ":",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "?",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "/",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": ";",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "'",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "18": {
148
+ "content": "`",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "19": {
156
+ "content": "[",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "20": {
164
+ "content": "]",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "21": {
172
+ "content": "£",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "22": {
180
+ "content": "€",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "23": {
188
+ "content": "$",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "24": {
196
+ "content": "*",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "25": {
204
+ "content": "%",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "26": {
212
+ "content": "&",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "27": {
220
+ "content": "=",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "28": {
228
+ "content": "+",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
  }
235
  },
236
+ "bos_token": "[CLS]",
237
+ "clean_up_tokenization_spaces": false,
238
  "cls_token": "[CLS]",
 
239
  "do_lower_case": false,
240
+ "eos_token": "[SEP]",
241
+ "keep_accents": true,
242
  "mask_token": "[MASK]",
243
  "model_max_length": 512,
244
+ "pad_token": "<pad>",
245
+ "remove_space": true,
246
  "sep_token": "[SEP]",
247
+ "sp_model_kwargs": {},
248
+ "tokenizer_class": "AlbertTokenizer",
249
+ "unk_token": "<unk>"
 
250
  }