Hugging Face's logo

zpn
/
dna_single_bp_tokenizer

Model card Files
xet
Community
zpn commited on
Commit
0f244e7
·
1 Parent(s): 423f3bd

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +23 -91
  2. tokenizer_config.json +1 -1
tokenizer.json CHANGED
@@ -5,7 +5,7 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "content": "[UNK]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
@@ -14,7 +14,7 @@
14
  },
15
  {
16
  "id": 1,
17
- "content": "[CLS]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
@@ -23,25 +23,7 @@
23
  },
24
  {
25
  "id": 2,
26
- "content": "[SEP]",
27
- "single_word": false,
28
- "lstrip": false,
29
- "rstrip": false,
30
- "normalized": false,
31
- "special": true
32
- },
33
- {
34
- "id": 3,
35
- "content": "[PAD]",
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,
@@ -49,80 +31,30 @@
49
  "special": true
50
  }
51
  ],
52
- "normalizer": null,
53
- "pre_tokenizer": null,
54
- "post_processor": {
55
- "type": "TemplateProcessing",
56
- "single": [
57
- {
58
- "SpecialToken": {
59
- "id": "[CLS]",
60
- "type_id": 0
61
- }
62
- },
63
- {
64
- "Sequence": {
65
- "id": "A",
66
- "type_id": 0
67
- }
68
- },
69
- {
70
- "SpecialToken": {
71
- "id": "[SEP]",
72
- "type_id": 0
73
- }
74
- }
75
- ],
76
- "pair": [
77
- {
78
- "Sequence": {
79
- "id": "A",
80
- "type_id": 0
81
- }
82
- },
83
- {
84
- "Sequence": {
85
- "id": "B",
86
- "type_id": 1
87
- }
88
- }
89
- ],
90
- "special_tokens": {
91
- "[CLS]": {
92
- "id": "[CLS]",
93
- "ids": [
94
- 1
95
- ],
96
- "tokens": [
97
- "[CLS]"
98
- ]
99
- },
100
- "[SEP]": {
101
- "id": "[SEP]",
102
- "ids": [
103
- 2
104
- ],
105
- "tokens": [
106
- "[SEP]"
107
- ]
108
- }
109
- }
110
  },
 
111
  "decoder": null,
112
  "model": {
113
- "type": "WordLevel",
 
 
 
 
 
114
  "vocab": {
115
- "[UNK]": 0,
116
- "[CLS]": 1,
117
- "[SEP]": 2,
118
- "[PAD]": 3,
119
- "[MASK]": 4,
120
- "A": 5,
121
- "C": 6,
122
- "G": 7,
123
- "N": 8,
124
- "T": 9
125
  },
126
- "unk_token": "[UNK]"
127
  }
128
  }
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
+ "content": "[PAD]",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
 
14
  },
15
  {
16
  "id": 1,
17
+ "content": "[MASK]",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
 
23
  },
24
  {
25
  "id": 2,
26
+ "content": "[UNK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
 
31
  "special": true
32
  }
33
  ],
34
+ "normalizer": {
35
+ "type": "Lowercase"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "Whitespace"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  },
40
+ "post_processor": null,
41
  "decoder": null,
42
  "model": {
43
+ "type": "BPE",
44
+ "dropout": null,
45
+ "unk_token": "[UNK]",
46
+ "continuing_subword_prefix": null,
47
+ "end_of_word_suffix": null,
48
+ "fuse_unk": false,
49
  "vocab": {
50
+ "[PAD]": 0,
51
+ "[MASK]": 1,
52
+ "[UNK]": 2,
53
+ "a": 3,
54
+ "c": 4,
55
+ "g": 5,
56
+ "t": 6
 
 
 
57
  },
58
+ "merges": []
59
  }
60
  }
tokenizer_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "cls_token": "[CLS]",
3
  "mask_token": "[MASK]",
4
- "model_max_length": 1000,
5
  "pad_token": "[PAD]",
6
  "sep_token": "[SEP]",
7
  "tokenizer_class": "PreTrainedTokenizerFast",
 
1
  {
2
  "cls_token": "[CLS]",
3
  "mask_token": "[MASK]",
4
+ "model_max_length": 1000000000000000019884624838656,
5
  "pad_token": "[PAD]",
6
  "sep_token": "[SEP]",
7
  "tokenizer_class": "PreTrainedTokenizerFast",