Hugging Face's logo

kotsonor
/
BiomedBERT-Amyloid

Text Classification
Transformers
Safetensors
English
bert
biomedicine
classification
amyloids
antibodies
pubmed
Model card Files
xet
Community
kotsonor commited on
Commit
55979af
·
verified ·
1 Parent(s): 9164c08

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +5 -0
  2. special_tokens_map.json +42 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +94 -0
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[JOURNAL_END]": 28897,
3
+ "[KEY]": 28895,
4
+ "[TITLE_END]": 28896
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[KEY]",
4
+ "[TITLE_END]",
5
+ "[JOURNAL_END]"
6
+ ],
7
+ "cls_token": {
8
+ "content": "[CLS]",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "mask_token": {
15
+ "content": "[MASK]",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": {
22
+ "content": "[PAD]",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "sep_token": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
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
+ "28895": {
44
+ "content": "[KEY]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "28896": {
52
+ "content": "[TITLE_END]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "28897": {
60
+ "content": "[JOURNAL_END]",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "[KEY]",
70
+ "[TITLE_END]",
71
+ "[JOURNAL_END]"
72
+ ],
73
+ "clean_up_tokenization_spaces": true,
74
+ "cls_token": "[CLS]",
75
+ "do_basic_tokenize": true,
76
+ "do_lower_case": true,
77
+ "extra_special_tokens": {},
78
+ "mask_token": "[MASK]",
79
+ "max_length": 350,
80
+ "model_max_length": 1000000000000000019884624838656,
81
+ "never_split": null,
82
+ "pad_to_multiple_of": null,
83
+ "pad_token": "[PAD]",
84
+ "pad_token_type_id": 0,
85
+ "padding_side": "right",
86
+ "sep_token": "[SEP]",
87
+ "stride": 0,
88
+ "strip_accents": null,
89
+ "tokenize_chinese_chars": true,
90
+ "tokenizer_class": "BertTokenizer",
91
+ "truncation_side": "right",
92
+ "truncation_strategy": "longest_first",
93
+ "unk_token": "[UNK]"
94
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff