Hugging Face's logo

michaelm16
/
CRISPR-viva

Safetensors
biology
Model card Files Community
michaelm16 commited on
Commit
6ab0dcc
·
verified ·
1 Parent(s): 43debb5

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. special_tokens_map.json +37 -0
  3. tokenizer.json +76 -0
  4. tokenizer_config.json +36 -0
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- license: apache-2.0
3
  datasets:
4
  - michaelm16/GuideRNA-3B
 
5
  tags:
6
  - biology
7
  ---
 
1
  ---
 
2
  datasets:
3
  - michaelm16/GuideRNA-3B
4
+ license: apache-2.0
5
  tags:
6
  - biology
7
  ---
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "E",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "N",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "N",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "F",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "N",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "N",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "E",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "F",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "NFD"
39
+ },
40
+ {
41
+ "type": "Strip",
42
+ "strip_left": true,
43
+ "strip_right": true
44
+ }
45
+ ]
46
+ },
47
+ "pre_tokenizer": {
48
+ "type": "Split",
49
+ "pattern": {
50
+ "Regex": "[a-zA-Z]"
51
+ },
52
+ "behavior": "Isolated",
53
+ "invert": false
54
+ },
55
+ "post_processor": null,
56
+ "decoder": {
57
+ "type": "WordPiece",
58
+ "prefix": "",
59
+ "cleanup": true
60
+ },
61
+ "model": {
62
+ "type": "WordPiece",
63
+ "unk_token": "N",
64
+ "continuing_subword_prefix": "##",
65
+ "max_input_chars_per_word": 100,
66
+ "vocab": {
67
+ "N": 0,
68
+ "E": 1,
69
+ "F": 2,
70
+ "A": 3,
71
+ "C": 4,
72
+ "G": 5,
73
+ "T": 6
74
+ }
75
+ }
76
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "N",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "E",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "F",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "clean_up_tokenization_spaces": true,
29
+ "cls_token": "E",
30
+ "mask_token": "N",
31
+ "model_max_length": 64,
32
+ "pad_token": "N",
33
+ "sep_token": "F",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "N"
36
+ }