Hugging Face's logo

dsrestrepo
/
BERT_Lab_Values_10B_lab_id_no_repetition

Fill-Mask
Transformers
Safetensors
bert
Inference Endpoints
Model card Files Community
dsrestrepo commited on
Commit
7ce14db
•
1 Parent(s): 32a8ed9

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +3 -0
  2. special_tokens_map.json +37 -0
  3. tokenizer_config.json +57 -0
  4. vocab.txt +84 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[UNK]": 84
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "81": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "82": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "83": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "84": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
vocab.txt ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [PAD]
2
+ BicH
3
+ CrtA
4
+ PotH
5
+ SodD
6
+ UreG
7
+ HgbI
8
+ PltA
9
+ WbcB
10
+ BicE
11
+ PotJ
12
+ SodA
13
+ UreH
14
+ PltC
15
+ WbcD
16
+ BicF
17
+ CrtB
18
+ UreI
19
+ WbcE
20
+ BicD
21
+ HgbH
22
+ PltB
23
+ WbcC
24
+ CrtC
25
+ PotE
26
+ SodB
27
+ UreC
28
+ HgbJ
29
+ PltH
30
+ WbcF
31
+ BicC
32
+ PotF
33
+ UreB
34
+ SodC
35
+ SodG
36
+ BicB
37
+ CrtD
38
+ PotB
39
+ SodI
40
+ PltG
41
+ SodJ
42
+ PltF
43
+ WbcG
44
+ PotG
45
+ PltE
46
+ BicG
47
+ PotC
48
+ SodE
49
+ PltD
50
+ BicA
51
+ CrtG
52
+ WbcH
53
+ PotD
54
+ WbcA
55
+ BicI
56
+ UreA
57
+ WbcI
58
+ HgbG
59
+ PltJ
60
+ WbcJ
61
+ PltI
62
+ BicJ
63
+ HgbF
64
+ HgbD
65
+ HgbE
66
+ HgbC
67
+ PotA
68
+ HgbA
69
+ HgbB
70
+ SodF
71
+ SodH
72
+ CrtI
73
+ UreJ
74
+ CrtJ
75
+ CrtH
76
+ PotI
77
+ UreF
78
+ UreE
79
+ UreD
80
+ CrtE
81
+ CrtF
82
+ [CLS]
83
+ [SEP]
84
+ [MASK]