berendg commited on
Commit
3f7ee1e
1 Parent(s): 6e897f7

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +15 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +22 -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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
16
+ "pad_token": "<pad>",
17
+ "remove_space": true,
18
+ "sep_token": "[SEP]",
19
+ "special_tokens_map_file": "SzegedAI/babylm-strict-small-mlsm/special_tokens_map.json",
20
+ "tokenizer_class": "AlbertTokenizer",
21
+ "unk_token": "<unk>"
22
+ }