cdhinrichs commited on
Commit
ad528b9
1 Parent(s): edeefbc

Added tokenizer configs

Browse files
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:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
3
+ size 760289
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 512,
16
+ "name_or_path": "albert-large-v2",
17
+ "pad_token": "<pad>",
18
+ "remove_space": true,
19
+ "sep_token": "[SEP]",
20
+ "special_tokens_map_file": null,
21
+ "tokenizer_class": "AlbertTokenizer",
22
+ "unk_token": "<unk>"
23
+ }