shrutisingh commited on
Commit
1bf2d90
1 Parent(s): b03f8a4

Upload 4 files

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +16 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +15 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[TTL]",
4
+ "[ABS]",
5
+ "[INTR]",
6
+ "[MET]",
7
+ "[RES]",
8
+ "[RW]",
9
+ "[CONC]"
10
+ ],
11
+ "cls_token": "[CLS]",
12
+ "mask_token": "[MASK]",
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "unk_token": "[UNK]"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "allenai/scibert_scivocab_cased",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff