Reshma27 commited on
Commit
93a04aa
1 Parent(s): a44fdd4

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +7 -0
  2. tokenizer_config.json +17 -0
  3. 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_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "model_max_length": 512,
8
+ "name_or_path": "microsoft/layoutlm-base-uncased",
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": "C:\\Users\\Administrator/.cache\\huggingface\\transformers\\48c3f426580c1b3278dbebb8c8dd372ea1549792f092b4f6fae1e21881c2cbd9.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
13
+ "strip_accents": null,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "LayoutLMTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff