Bijayab commited on
Commit
04c9807
1 Parent(s): 450f500

Upload 4 files

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<cls>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "<sep>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
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
+ "add_prefix_space": false,
3
+ "bos_token": "<cls>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "<sep>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "max_length": 1000,
10
+ "model_max_length": 1000,
11
+ "pad_to_multiple_of": null,
12
+ "pad_token": "<pad>",
13
+ "pad_token_type_id": 0,
14
+ "padding_side": "right",
15
+ "sep_token": "</s>",
16
+ "stride": 0,
17
+ "tokenizer_class": "BartTokenizer",
18
+ "trim_offsets": true,
19
+ "truncation_side": "right",
20
+ "truncation_strategy": "longest_first",
21
+ "unk_token": "<unk>"
22
+ }
unigram.json ADDED
The diff for this file is too large to render. See raw diff