Hugging Face's logo

knowledgator
/
SMILES-FAST-TOKENIZER

Model card Files Community
BioMike commited on
Commit
c1f9196
·
verified ·
1 Parent(s): 9675f64

Upload 3 files

Browse files

tokenizer uploaded

Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +287 -0
  3. tokenizer_config.json +54 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>",
6
+ "mask_token": "<mask>"
7
+ }
tokenizer.json ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<bos>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
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": null,
53
+ "pre_tokenizer": {
54
+ "type": "Sequence",
55
+ "pretokenizers": [
56
+ {
57
+ "type": "Split",
58
+ "pattern": {
59
+ "Regex": "(\\[[^\\]]+]|<[^>]+>|Br?|Cl?|N|O|S|P|F|H|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\\\\\|\\/|:|~|@|\\?|\\*|\\$|\\%[0-9]{2}|[0-9])"
60
+ },
61
+ "behavior": "Isolated",
62
+ "invert": false
63
+ },
64
+ {
65
+ "type": "Split",
66
+ "pattern": {
67
+ "Regex": "\\[|\\]|0|1|2|3|4|5|6|7|8|9|-|\\+|H|@"
68
+ },
69
+ "behavior": "Isolated",
70
+ "invert": false
71
+ }
72
+ ]
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ },
89
+ {
90
+ "SpecialToken": {
91
+ "id": "<eos>",
92
+ "type_id": 0
93
+ }
94
+ }
95
+ ],
96
+ "pair": [
97
+ {
98
+ "Sequence": {
99
+ "id": "A",
100
+ "type_id": 0
101
+ }
102
+ },
103
+ {
104
+ "Sequence": {
105
+ "id": "B",
106
+ "type_id": 1
107
+ }
108
+ }
109
+ ],
110
+ "special_tokens": {
111
+ "<bos>": {
112
+ "id": "<bos>",
113
+ "ids": [
114
+ 2
115
+ ],
116
+ "tokens": [
117
+ "<bos>"
118
+ ]
119
+ },
120
+ "<eos>": {
121
+ "id": "<eos>",
122
+ "ids": [
123
+ 1
124
+ ],
125
+ "tokens": [
126
+ "<eos>"
127
+ ]
128
+ },
129
+ "<pad>": {
130
+ "id": "<pad>",
131
+ "ids": [
132
+ 0
133
+ ],
134
+ "tokens": [
135
+ "<pad>"
136
+ ]
137
+ }
138
+ }
139
+ },
140
+ "decoder": {
141
+ "type": "BPEDecoder",
142
+ "suffix": "</w>"
143
+ },
144
+ "model": {
145
+ "type": "WordLevel",
146
+ "vocab": {
147
+ "<pad>": 0,
148
+ "<eos>": 1,
149
+ "<bos>": 2,
150
+ "<unk>": 3,
151
+ "<mask>": 4,
152
+ "C": 5,
153
+ "=": 6,
154
+ "(": 7,
155
+ ")": 8,
156
+ "O": 9,
157
+ "N": 10,
158
+ "1": 11,
159
+ "2": 12,
160
+ "3": 13,
161
+ "4": 14,
162
+ "F": 15,
163
+ "S": 16,
164
+ "<BASE>": 17,
165
+ "<SYST>": 18,
166
+ "<TRAD>": 19,
167
+ "5": 20,
168
+ "Cl": 21,
169
+ "[": 22,
170
+ "]": 23,
171
+ ".": 24,
172
+ "6": 25,
173
+ "7": 26,
174
+ "-": 27,
175
+ "+": 28,
176
+ "#": 29,
177
+ "Br": 30,
178
+ "8": 31,
179
+ "9": 32,
180
+ "P": 33,
181
+ "H": 34,
182
+ "I": 35,
183
+ "Si": 36,
184
+ "B": 37,
185
+ "Na": 38,
186
+ "Y": 39,
187
+ "Ir": 40,
188
+ "Pt": 41,
189
+ "K": 42,
190
+ "Se": 43,
191
+ "Li": 44,
192
+ "W": 45,
193
+ "Sn": 46,
194
+ "V": 47,
195
+ "Zr": 48,
196
+ "Zn": 49,
197
+ "Cu": 50,
198
+ "Fe": 51,
199
+ "%": 52,
200
+ "Ti": 53,
201
+ "Pd": 54,
202
+ "Co": 55,
203
+ "Mg": 56,
204
+ "Al": 57,
205
+ "Ni": 58,
206
+ "Ge": 59,
207
+ "Ru": 60,
208
+ "Ca": 61,
209
+ "U": 62,
210
+ "Mn": 63,
211
+ "Cr": 64,
212
+ "Au": 65,
213
+ "Ag": 66,
214
+ "As": 67,
215
+ "Te": 68,
216
+ "Mo": 69,
217
+ "Ac": 70,
218
+ "0": 71,
219
+ "Tb": 72,
220
+ "f": 73,
221
+ "Rh": 74,
222
+ "g": 75,
223
+ "Cs": 76,
224
+ "Rf": 77,
225
+ "Ar": 78,
226
+ "Sb": 79,
227
+ "Rb": 80,
228
+ "Ba": 81,
229
+ "Os": 82,
230
+ "Re": 83,
231
+ "Gd": 84,
232
+ "Cd": 85,
233
+ "Bi": 86,
234
+ "Pb": 87,
235
+ "In": 88,
236
+ "Ga": 89,
237
+ "Ce": 90,
238
+ "La": 91,
239
+ "Eu": 92,
240
+ "Tl": 93,
241
+ "Tc": 94,
242
+ "Nb": 95,
243
+ "Sr": 96,
244
+ "Ta": 97,
245
+ "Nd": 98,
246
+ "Pr": 99,
247
+ "Yb": 100,
248
+ "Sm": 101,
249
+ "Be": 102,
250
+ "Sc": 103,
251
+ "Dy": 104,
252
+ "Lu": 105,
253
+ "Fm": 106,
254
+ "Er": 107,
255
+ "Th": 108,
256
+ "o": 109,
257
+ "Tm": 110,
258
+ "At": 111,
259
+ "No": 112,
260
+ "Po": 113,
261
+ "Cm": 114,
262
+ "Sg": 115,
263
+ "Xe": 116,
264
+ "Np": 117,
265
+ "Lr": 118,
266
+ "Pu": 119,
267
+ "Pm": 120,
268
+ "Cf": 121,
269
+ "e": 122,
270
+ "Am": 123,
271
+ "Es": 124,
272
+ "Pa": 125,
273
+ "Ne": 126,
274
+ "Bk": 127,
275
+ "Db": 128,
276
+ "Mt": 129,
277
+ "Kr": 130,
278
+ "Rn": 131,
279
+ "s": 132,
280
+ "Bh": 133,
281
+ "Md": 134,
282
+ "Ra": 135,
283
+ "Fr": 136
284
+ },
285
+ "unk_token": "<unk>"
286
+ }
287
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<bos>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
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
+ "bos_token": "<bos>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "eos_token": "<eos>",
47
+ "model_max_length": 512,
48
+ "pad_token": "<pad>",
49
+ "padding_side": "right",
50
+ "tokenizer_class": "PreTrainedTokenizerFast",
51
+ "truncation_side": "right",
52
+ "unk_token": "<unk>",
53
+ "mask_token": "<mask>"
54
+ }