Hugging Face's logo

nepp1d0
/
smiles-target-interaction

Text Classification
Transformers
PyTorch
TensorBoard
bert
Model card Files
xet
Metrics Community
1
nepp1d0 commited on
Commit
8b73244
·
1 Parent(s): c8f691b

add tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +1 -0
  2. tokenizer.json +202 -0
  3. tokenizer_config.json +1 -0
  4. vocab.txt +70 -0
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[PAD]",
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": "WhitespaceSplit"
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
+ "Sequence": {
87
+ "id": "A",
88
+ "type_id": 0
89
+ }
90
+ },
91
+ {
92
+ "Sequence": {
93
+ "id": "B",
94
+ "type_id": 1
95
+ }
96
+ }
97
+ ],
98
+ "special_tokens": {
99
+ "[CLS]": {
100
+ "id": "[CLS]",
101
+ "ids": [
102
+ 2
103
+ ],
104
+ "tokens": [
105
+ "[CLS]"
106
+ ]
107
+ },
108
+ "[SEP]": {
109
+ "id": "[SEP]",
110
+ "ids": [
111
+ 3
112
+ ],
113
+ "tokens": [
114
+ "[SEP]"
115
+ ]
116
+ }
117
+ }
118
+ },
119
+ "decoder": {
120
+ "type": "WordPiece",
121
+ "prefix": "##",
122
+ "cleanup": true
123
+ },
124
+ "model": {
125
+ "type": "WordPiece",
126
+ "unk_token": "[UNK]",
127
+ "continuing_subword_prefix": "##",
128
+ "max_input_chars_per_word": 100,
129
+ "vocab": {
130
+ "[UNK]": 0,
131
+ "[PAD]": 1,
132
+ "[CLS]": 2,
133
+ "[SEP]": 3,
134
+ "[MASK]": 4,
135
+ "\"": 5,
136
+ "#": 6,
137
+ "(": 7,
138
+ ")": 8,
139
+ "+": 9,
140
+ "-": 10,
141
+ ".": 11,
142
+ "/": 12,
143
+ "1": 13,
144
+ "2": 14,
145
+ "3": 15,
146
+ "4": 16,
147
+ "5": 17,
148
+ "6": 18,
149
+ "7": 19,
150
+ "8": 20,
151
+ "9": 21,
152
+ "=": 22,
153
+ "@": 23,
154
+ "A": 24,
155
+ "B": 25,
156
+ "C": 26,
157
+ "D": 27,
158
+ "E": 28,
159
+ "F": 29,
160
+ "G": 30,
161
+ "H": 31,
162
+ "I": 32,
163
+ "K": 33,
164
+ "L": 34,
165
+ "M": 35,
166
+ "N": 36,
167
+ "O": 37,
168
+ "P": 38,
169
+ "Q": 39,
170
+ "R": 40,
171
+ "S": 41,
172
+ "T": 42,
173
+ "V": 43,
174
+ "W": 44,
175
+ "X": 45,
176
+ "Y": 46,
177
+ "[": 47,
178
+ "\\": 48,
179
+ "]": 49,
180
+ "a": 50,
181
+ "c": 51,
182
+ "i": 52,
183
+ "l": 53,
184
+ "n": 54,
185
+ "o": 55,
186
+ "r": 56,
187
+ "s": 57,
188
+ "##O": 58,
189
+ "##\"": 59,
190
+ "##S": 60,
191
+ "##E": 61,
192
+ "##P": 62,
193
+ "##]": 63,
194
+ "##C": 64,
195
+ "##N": 65,
196
+ "##B": 66,
197
+ "##[": 67,
198
+ "##c": 68,
199
+ "##F": 69
200
+ }
201
+ }
202
+ }
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "tokenizer_class": "BertTokenizer"}
vocab.txt ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [UNK]
2
+ [PAD]
3
+ [CLS]
4
+ [SEP]
5
+ [MASK]
6
+ "
7
+ #
8
+ (
9
+ )
10
+ +
11
+ -
12
+ .
13
+ /
14
+ 1
15
+ 2
16
+ 3
17
+ 4
18
+ 5
19
+ 6
20
+ 7
21
+ 8
22
+ 9
23
+ =
24
+ @
25
+ A
26
+ B
27
+ C
28
+ D
29
+ E
30
+ F
31
+ G
32
+ H
33
+ I
34
+ K
35
+ L
36
+ M
37
+ N
38
+ O
39
+ P
40
+ Q
41
+ R
42
+ S
43
+ T
44
+ V
45
+ W
46
+ X
47
+ Y
48
+ [
49
+ \
50
+ ]
51
+ a
52
+ c
53
+ i
54
+ l
55
+ n
56
+ o
57
+ r
58
+ s
59
+ ##O
60
+ ##"
61
+ ##S
62
+ ##E
63
+ ##P
64
+ ##]
65
+ ##C
66
+ ##N
67
+ ##B
68
+ ##[
69
+ ##c
70
+ ##F