Hugging Face's logo

mjhwang
/
roberta-reg-eval

Text Classification
Transformers
Safetensors
roberta
text-embeddings-inference
Model card Files
xet
Community
mjhwang commited on
Commit
1d50836
·
verified ·
1 Parent(s): 265de7d

Upload tokenizer

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +55 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +84 -0
  5. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "[A]": 32001,
3
+ "[TYPE]": 32000
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[TYPE]",
4
+ "[A]"
5
+ ],
6
+ "bos_token": {
7
+ "content": "[CLS]",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "cls_token": {
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "mask_token": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "[PAD]",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "sep_token": {
42
+ "content": "[SEP]",
43
+ "lstrip": false,
44
+ "normalized": false,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "unk_token": {
49
+ "content": "[UNK]",
50
+ "lstrip": false,
51
+ "normalized": false,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ }
55
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
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
+ "32000": {
44
+ "content": "[TYPE]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32001": {
52
+ "content": "[A]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "[TYPE]",
62
+ "[A]"
63
+ ],
64
+ "bos_token": "[CLS]",
65
+ "clean_up_tokenization_spaces": false,
66
+ "cls_token": "[CLS]",
67
+ "do_basic_tokenize": true,
68
+ "do_lower_case": false,
69
+ "eos_token": "[SEP]",
70
+ "extra_special_tokens": {},
71
+ "mask_token": "[MASK]",
72
+ "max_length": 512,
73
+ "model_max_length": 512,
74
+ "never_split": null,
75
+ "pad_token": "[PAD]",
76
+ "sep_token": "[SEP]",
77
+ "stride": 0,
78
+ "strip_accents": null,
79
+ "tokenize_chinese_chars": true,
80
+ "tokenizer_class": "BertTokenizer",
81
+ "truncation_side": "right",
82
+ "truncation_strategy": "longest_first",
83
+ "unk_token": "[UNK]"
84
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff