14-07-22 commited on
Commit
6e8dd69
1 Parent(s): 4465b22

add tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<answer>": 28896,
3
+ "<k>": 28895,
4
+ "<unk>": 28897
5
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<k>",
4
+ "<answer>",
5
+ "<unk>"
6
+ ],
7
+ "cls_token": "[CLS]",
8
+ "mask_token": "[MASK]",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "unk_token": "[UNK]"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "max_length": 256,
7
+ "name_or_path": "michiyasunaga/BioLinkBERT-base",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": null,
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff