Hugging Face's logo

DT4H
/
CardioBERTa.en

PyTorch
roberta
Model card Files
xet
Community
1
23pablo97 commited on
Commit
06719ed
·
verified ·
1 Parent(s): 9a290f8

Upload tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +51 -0
  3. tokenizer_config.json +107 -0
  4. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": {
55
+ "__type": "AddedToken",
56
+ "content": "<s>",
57
+ "lstrip": false,
58
+ "normalized": true,
59
+ "rstrip": false,
60
+ "single_word": false
61
+ },
62
+ "eos_token": {
63
+ "__type": "AddedToken",
64
+ "content": "</s>",
65
+ "lstrip": false,
66
+ "normalized": true,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ },
70
+ "errors": "replace",
71
+ "mask_token": {
72
+ "__type": "AddedToken",
73
+ "content": "<mask>",
74
+ "lstrip": true,
75
+ "normalized": true,
76
+ "rstrip": false,
77
+ "single_word": false
78
+ },
79
+ "max_len": 512,
80
+ "model_max_length": 512,
81
+ "pad_token": {
82
+ "__type": "AddedToken",
83
+ "content": "<pad>",
84
+ "lstrip": false,
85
+ "normalized": true,
86
+ "rstrip": false,
87
+ "single_word": false
88
+ },
89
+ "sep_token": {
90
+ "__type": "AddedToken",
91
+ "content": "</s>",
92
+ "lstrip": false,
93
+ "normalized": true,
94
+ "rstrip": false,
95
+ "single_word": false
96
+ },
97
+ "tokenizer_class": "RobertaTokenizer",
98
+ "trim_offsets": true,
99
+ "unk_token": {
100
+ "__type": "AddedToken",
101
+ "content": "<unk>",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false
106
+ }
107
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff