Hugging Face's logo

xchen16
/
g2pt-guacamol-large-bfs

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
xchen16 commited on
Commit
84712d5
·
verified ·
1 Parent(s): de11ea3

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +7 -0
  2. special_tokens_map.json +25 -0
  3. tokenizer.json +183 -0
  4. tokenizer_config.json +56 -0
  5. vocab.json +1 -0
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 116,
3
+ "[MASK]": 114,
4
+ "[PAD]": 113,
5
+ "[SEP]": 115,
6
+ "[UNK]": 112
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": {
4
+ "content": "[MASK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "pad_token": {
11
+ "content": "[PAD]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "sep_token": "[SEP]",
18
+ "unk_token": {
19
+ "content": "[UNK]",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 112,
8
+ "content": "[UNK]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 113,
17
+ "content": "[PAD]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 114,
26
+ "content": "[MASK]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 115,
35
+ "content": "[SEP]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 116,
44
+ "content": "[CLS]",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ }
51
+ ],
52
+ "normalizer": {
53
+ "type": "Sequence",
54
+ "normalizers": []
55
+ },
56
+ "pre_tokenizer": {
57
+ "type": "WhitespaceSplit"
58
+ },
59
+ "post_processor": null,
60
+ "decoder": {
61
+ "type": "WordPiece",
62
+ "prefix": "##",
63
+ "cleanup": true
64
+ },
65
+ "model": {
66
+ "type": "WordLevel",
67
+ "vocab": {
68
+ "<boc>": 0,
69
+ "<eoc>": 1,
70
+ "<sepc>": 2,
71
+ "<bog>": 3,
72
+ "<eog>": 4,
73
+ "<sepg>": 5,
74
+ "IDX_0": 6,
75
+ "IDX_1": 7,
76
+ "IDX_2": 8,
77
+ "IDX_3": 9,
78
+ "IDX_4": 10,
79
+ "IDX_5": 11,
80
+ "IDX_6": 12,
81
+ "IDX_7": 13,
82
+ "IDX_8": 14,
83
+ "IDX_9": 15,
84
+ "IDX_10": 16,
85
+ "IDX_11": 17,
86
+ "IDX_12": 18,
87
+ "IDX_13": 19,
88
+ "IDX_14": 20,
89
+ "IDX_15": 21,
90
+ "IDX_16": 22,
91
+ "IDX_17": 23,
92
+ "IDX_18": 24,
93
+ "IDX_19": 25,
94
+ "IDX_20": 26,
95
+ "IDX_21": 27,
96
+ "IDX_22": 28,
97
+ "IDX_23": 29,
98
+ "IDX_24": 30,
99
+ "IDX_25": 31,
100
+ "IDX_26": 32,
101
+ "IDX_27": 33,
102
+ "IDX_28": 34,
103
+ "IDX_29": 35,
104
+ "IDX_30": 36,
105
+ "IDX_31": 37,
106
+ "IDX_32": 38,
107
+ "IDX_33": 39,
108
+ "IDX_34": 40,
109
+ "IDX_35": 41,
110
+ "IDX_36": 42,
111
+ "IDX_37": 43,
112
+ "IDX_38": 44,
113
+ "IDX_39": 45,
114
+ "IDX_40": 46,
115
+ "IDX_41": 47,
116
+ "IDX_42": 48,
117
+ "IDX_43": 49,
118
+ "IDX_44": 50,
119
+ "IDX_45": 51,
120
+ "IDX_46": 52,
121
+ "IDX_47": 53,
122
+ "IDX_48": 54,
123
+ "IDX_49": 55,
124
+ "IDX_50": 56,
125
+ "IDX_51": 57,
126
+ "IDX_52": 58,
127
+ "IDX_53": 59,
128
+ "IDX_54": 60,
129
+ "IDX_55": 61,
130
+ "IDX_56": 62,
131
+ "IDX_57": 63,
132
+ "IDX_58": 64,
133
+ "IDX_59": 65,
134
+ "IDX_60": 66,
135
+ "IDX_61": 67,
136
+ "IDX_62": 68,
137
+ "IDX_63": 69,
138
+ "IDX_64": 70,
139
+ "IDX_65": 71,
140
+ "IDX_66": 72,
141
+ "IDX_67": 73,
142
+ "IDX_68": 74,
143
+ "IDX_69": 75,
144
+ "IDX_70": 76,
145
+ "IDX_71": 77,
146
+ "IDX_72": 78,
147
+ "IDX_73": 79,
148
+ "IDX_74": 80,
149
+ "IDX_75": 81,
150
+ "IDX_76": 82,
151
+ "IDX_77": 83,
152
+ "IDX_78": 84,
153
+ "IDX_79": 85,
154
+ "IDX_80": 86,
155
+ "IDX_81": 87,
156
+ "IDX_82": 88,
157
+ "IDX_83": 89,
158
+ "IDX_84": 90,
159
+ "IDX_85": 91,
160
+ "IDX_86": 92,
161
+ "IDX_87": 93,
162
+ "IDX_88": 94,
163
+ "IDX_89": 95,
164
+ "ATOM_C": 96,
165
+ "ATOM_N": 97,
166
+ "ATOM_O": 98,
167
+ "ATOM_F": 99,
168
+ "ATOM_B": 100,
169
+ "ATOM_Br": 101,
170
+ "ATOM_Cl": 102,
171
+ "ATOM_I": 103,
172
+ "ATOM_P": 104,
173
+ "ATOM_S": 105,
174
+ "ATOM_Se": 106,
175
+ "ATOM_Si": 107,
176
+ "BOND_SINGLE": 108,
177
+ "BOND_DOUBLE": 109,
178
+ "BOND_TRIPLE": 110,
179
+ "BOND_AROMATIC": 111
180
+ },
181
+ "unk_token": "[UNK]"
182
+ }
183
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "112": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "113": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "114": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "115": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "116": {
36
+ "content": "[CLS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 614,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<boc>":0,"<eoc>":1,"<sepc>":2,"<bog>":3,"<eog>":4,"<sepg>":5,"IDX_0":6,"IDX_1":7,"IDX_2":8,"IDX_3":9,"IDX_4":10,"IDX_5":11,"IDX_6":12,"IDX_7":13,"IDX_8":14,"IDX_9":15,"IDX_10":16,"IDX_11":17,"IDX_12":18,"IDX_13":19,"IDX_14":20,"IDX_15":21,"IDX_16":22,"IDX_17":23,"IDX_18":24,"IDX_19":25,"IDX_20":26,"IDX_21":27,"IDX_22":28,"IDX_23":29,"IDX_24":30,"IDX_25":31,"IDX_26":32,"IDX_27":33,"IDX_28":34,"IDX_29":35,"IDX_30":36,"IDX_31":37,"IDX_32":38,"IDX_33":39,"IDX_34":40,"IDX_35":41,"IDX_36":42,"IDX_37":43,"IDX_38":44,"IDX_39":45,"IDX_40":46,"IDX_41":47,"IDX_42":48,"IDX_43":49,"IDX_44":50,"IDX_45":51,"IDX_46":52,"IDX_47":53,"IDX_48":54,"IDX_49":55,"IDX_50":56,"IDX_51":57,"IDX_52":58,"IDX_53":59,"IDX_54":60,"IDX_55":61,"IDX_56":62,"IDX_57":63,"IDX_58":64,"IDX_59":65,"IDX_60":66,"IDX_61":67,"IDX_62":68,"IDX_63":69,"IDX_64":70,"IDX_65":71,"IDX_66":72,"IDX_67":73,"IDX_68":74,"IDX_69":75,"IDX_70":76,"IDX_71":77,"IDX_72":78,"IDX_73":79,"IDX_74":80,"IDX_75":81,"IDX_76":82,"IDX_77":83,"IDX_78":84,"IDX_79":85,"IDX_80":86,"IDX_81":87,"IDX_82":88,"IDX_83":89,"IDX_84":90,"IDX_85":91,"IDX_86":92,"IDX_87":93,"IDX_88":94,"IDX_89":95,"ATOM_C":96,"ATOM_N":97,"ATOM_O":98,"ATOM_F":99,"ATOM_B":100,"ATOM_Br":101,"ATOM_Cl":102,"ATOM_I":103,"ATOM_P":104,"ATOM_S":105,"ATOM_Se":106,"ATOM_Si":107,"BOND_SINGLE":108,"BOND_DOUBLE":109,"BOND_TRIPLE":110,"BOND_AROMATIC":111}