Hugging Face's logo

nurcan
/
tdk-tokenizer

Model card Files Community
nurcan commited on
Commit
d100c93
·
1 Parent(s): 1c92819

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +37 -0
  2. tokenizer.json +209 -0
  3. tokenizer_config.json +58 -0
  4. vocab.txt +59 -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
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[PAD]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[CLS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 4,
44
+ "content": "[MASK]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "BertNormalizer",
54
+ "clean_text": true,
55
+ "handle_chinese_chars": true,
56
+ "strip_accents": null,
57
+ "lowercase": true
58
+ },
59
+ "pre_tokenizer": {
60
+ "type": "BertPreTokenizer"
61
+ },
62
+ "post_processor": {
63
+ "type": "TemplateProcessing",
64
+ "single": [
65
+ {
66
+ "SpecialToken": {
67
+ "id": "[CLS]",
68
+ "type_id": 0
69
+ }
70
+ },
71
+ {
72
+ "Sequence": {
73
+ "id": "A",
74
+ "type_id": 0
75
+ }
76
+ },
77
+ {
78
+ "SpecialToken": {
79
+ "id": "[SEP]",
80
+ "type_id": 0
81
+ }
82
+ }
83
+ ],
84
+ "pair": [
85
+ {
86
+ "SpecialToken": {
87
+ "id": "[CLS]",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "SpecialToken": {
99
+ "id": "[SEP]",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "B",
106
+ "type_id": 1
107
+ }
108
+ },
109
+ {
110
+ "SpecialToken": {
111
+ "id": "[SEP]",
112
+ "type_id": 1
113
+ }
114
+ }
115
+ ],
116
+ "special_tokens": {
117
+ "[CLS]": {
118
+ "id": "[CLS]",
119
+ "ids": [
120
+ 2
121
+ ],
122
+ "tokens": [
123
+ "[CLS]"
124
+ ]
125
+ },
126
+ "[SEP]": {
127
+ "id": "[SEP]",
128
+ "ids": [
129
+ 3
130
+ ],
131
+ "tokens": [
132
+ "[SEP]"
133
+ ]
134
+ }
135
+ }
136
+ },
137
+ "decoder": {
138
+ "type": "WordPiece",
139
+ "prefix": "##",
140
+ "cleanup": true
141
+ },
142
+ "model": {
143
+ "type": "WordPiece",
144
+ "unk_token": "[UNK]",
145
+ "continuing_subword_prefix": "##",
146
+ "max_input_chars_per_word": 100,
147
+ "vocab": {
148
+ "[PAD]": 0,
149
+ "[UNK]": 1,
150
+ "[CLS]": 2,
151
+ "[SEP]": 3,
152
+ "[MASK]": 4,
153
+ "a": 5,
154
+ "b": 6,
155
+ "c": 7,
156
+ "e": 8,
157
+ "f": 9,
158
+ "i": 10,
159
+ "k": 11,
160
+ "l": 12,
161
+ "m": 13,
162
+ "n": 14,
163
+ "p": 15,
164
+ "r": 16,
165
+ "s": 17,
166
+ "u": 18,
167
+ "ı": 19,
168
+ "##c": 20,
169
+ "##ı": 21,
170
+ "##n": 22,
171
+ "##l": 23,
172
+ "##m": 24,
173
+ "##a": 25,
174
+ "##i": 26,
175
+ "##k": 27,
176
+ "##r": 28,
177
+ "##u": 29,
178
+ "##b": 30,
179
+ "##e": 31,
180
+ "##p": 32,
181
+ "##s": 33,
182
+ "ac": 34,
183
+ "##li": 35,
184
+ "acı": 36,
185
+ "el": 37,
186
+ "fi": 38,
187
+ "##ıl": 39,
188
+ "##nıl": 40,
189
+ "##ma": 41,
190
+ "##ir": 42,
191
+ "##is": 43,
192
+ "##kir": 44,
193
+ "##ub": 45,
194
+ "##ps": 46,
195
+ "acub": 47,
196
+ "##lik": 48,
197
+ "##lips": 49,
198
+ "##lilik": 50,
199
+ "acık": 51,
200
+ "acınıl": 52,
201
+ "ellips": 53,
202
+ "fikir": 54,
203
+ "acube": 55,
204
+ "acınılma": 56,
205
+ "ellipsis": 57,
206
+ "fikirlilik": 58
207
+ }
208
+ }
209
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
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": true,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ [UNK]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ a
7
+ b
8
+ c
9
+ e
10
+ f
11
+ i
12
+ k
13
+ l
14
+ m
15
+ n
16
+ p
17
+ r
18
+ s
19
+ u
20
+ ı
21
+ ##c
22
+ ##ı
23
+ ##n
24
+ ##l
25
+ ##m
26
+ ##a
27
+ ##i
28
+ ##k
29
+ ##r
30
+ ##u
31
+ ##b
32
+ ##e
33
+ ##p
34
+ ##s
35
+ ac
36
+ ##li
37
+ acı
38
+ el
39
+ fi
40
+ ##ıl
41
+ ##nıl
42
+ ##ma
43
+ ##ir
44
+ ##is
45
+ ##kir
46
+ ##ub
47
+ ##ps
48
+ acub
49
+ ##lik
50
+ ##lips
51
+ ##lilik
52
+ acık
53
+ acınıl
54
+ ellips
55
+ fikir
56
+ acube
57
+ acınılma
58
+ ellipsis
59
+ fikirlilik