ridhimamlds commited on
Commit
65253a0
1 Parent(s): fc72346

Upload 3 files

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +17 -0
  3. vocab.txt +0 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "lowercase": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "name_or_path": "l3cube-pune/marathi-bert-v2",
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "special_tokens_map_file": "special_tokens_map.json",
13
+ "strip_accents": false,
14
+ "tokenize_chinese_chars": true,
15
+ "tokenizer_class": "BertTokenizer",
16
+ "unk_token": "[UNK]"
17
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff