asi commited on
Commit
9860d40
1 Parent(s): 77a5aa4

:package: add tokenizer files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +15 -0
  2. spiece.model +3 -0
  3. tokenizer_config.json +21 -0
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": {
6
+ "content": "[MASK]",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "[SEP]",
14
+ "unk_token": "<unk>"
15
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:489ad3c92238a1fe0e771fb2cc3ddb319422ba1fc1ca9539358bce8a9f0ecaf9
3
+ size 761111
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "eos_token": "[SEP]",
6
+ "keep_accents": false,
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "[MASK]",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "pad_token": "<pad>",
16
+ "remove_space": true,
17
+ "sep_token": "[SEP]",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "AlbertTokenizer",
20
+ "unk_token": "<unk>"
21
+ }