prajwalJumde commited on
Commit
fa17b46
1 Parent(s): 662e270

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +36 -0
  4. vocab.txt +0 -0
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "cls_token_box": [
6
+ 0,
7
+ 0,
8
+ 0,
9
+ 0
10
+ ],
11
+ "do_basic_tokenize": true,
12
+ "do_lower_case": true,
13
+ "mask_token": "[MASK]",
14
+ "model_max_length": 512,
15
+ "never_split": null,
16
+ "only_label_first_subword": true,
17
+ "pad_token": "[PAD]",
18
+ "pad_token_box": [
19
+ 0,
20
+ 0,
21
+ 0,
22
+ 0
23
+ ],
24
+ "pad_token_label": -100,
25
+ "sep_token": "[SEP]",
26
+ "sep_token_box": [
27
+ 1000,
28
+ 1000,
29
+ 1000,
30
+ 1000
31
+ ],
32
+ "strip_accents": null,
33
+ "tokenize_chinese_chars": true,
34
+ "tokenizer_class": "LayoutLMv2Tokenizer",
35
+ "unk_token": "[UNK]"
36
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff