loki1234 commited on
Commit
b7a7fc6
1 Parent(s): 2f49aff

Upload 3 files

Browse files
Files changed (3) hide show
  1. added_tokens.json +12 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +22 -0
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_answer>": 57523,
3
+ "</s_question>": 57524,
4
+ "<no/>": 57525,
5
+ "<s_answer>": 57526,
6
+ "<s_docvqa>": 57527,
7
+ "<s_iitcdip>": 57528,
8
+ "<s_question>": 57529,
9
+ "<s_synthdog>": 57530,
10
+ "<sep/>": 57522,
11
+ "<yes/>": 57531
12
+ }
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": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "from_slow": true,
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "name_or_path": "loki1234/xenon-model",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }