cccornflake commited on
Commit
10e983c
1 Parent(s): 31ae7ba

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[BLK]": 30522
3
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[BLK]"
4
+ ],
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[BLK]",
9
+ "unk_token": "[UNK]"
10
+ }
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
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "max_length": 512,
8
+ "model_max_length": 512,
9
+ "num_labels": 3,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "LayoutLMTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff