EpsilonGreedy commited on
Commit
e953c6e
·
verified ·
1 Parent(s): 6aa4d3a

Upload processor

Browse files
Files changed (2) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +8 -1
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -10,12 +10,19 @@
10
  ],
11
  "is_local": false,
12
  "mask_token": "<mask>",
 
13
  "model_max_length": 1000000000000000019884624838656,
 
14
  "pad_token": "<pad>",
 
 
15
  "processor_class": "TrOCRProcessor",
16
  "sep_token": "</s>",
17
  "sp_model_kwargs": {},
18
- "tokenizer_class": "XLMRobertaTokenizer",
 
 
 
19
  "unk_id": 0,
20
  "unk_token": "<unk>"
21
  }
 
10
  ],
11
  "is_local": false,
12
  "mask_token": "<mask>",
13
+ "max_length": 64,
14
  "model_max_length": 1000000000000000019884624838656,
15
+ "pad_to_multiple_of": null,
16
  "pad_token": "<pad>",
17
+ "pad_token_type_id": 0,
18
+ "padding_side": "right",
19
  "processor_class": "TrOCRProcessor",
20
  "sep_token": "</s>",
21
  "sp_model_kwargs": {},
22
+ "stride": 0,
23
+ "tokenizer_class": "TokenizersBackend",
24
+ "truncation_side": "right",
25
+ "truncation_strategy": "longest_first",
26
  "unk_id": 0,
27
  "unk_token": "<unk>"
28
  }