haoanh98 commited on
Commit
dd996aa
1 Parent(s): d7ed0ca

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<doc>": 64001,
3
+ "<mask>": 64000
4
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "name_or_path": "vinai/bartpho-word-base",
7
+ "pad_token": "<pad>",
8
+ "sep_token": "</s>",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "PhobertTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff