anhdang000 commited on
Commit
0b9c9db
·
verified ·
1 Parent(s): b9255f9

Upload processor

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +7 -0
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 512
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 1024,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 1024
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -122,11 +122,18 @@
122
  "cls_token": "<s>",
123
  "eos_token": "</s>",
124
  "mask_token": "<mask>",
 
125
  "model_max_length": 1000000000000000019884624838656,
 
126
  "pad_token": "<pad>",
 
 
127
  "processor_class": "DonutProcessor",
128
  "sep_token": "</s>",
129
  "sp_model_kwargs": {},
 
130
  "tokenizer_class": "XLMRobertaTokenizer",
 
 
131
  "unk_token": "<unk>"
132
  }
 
122
  "cls_token": "<s>",
123
  "eos_token": "</s>",
124
  "mask_token": "<mask>",
125
+ "max_length": 512,
126
  "model_max_length": 1000000000000000019884624838656,
127
+ "pad_to_multiple_of": null,
128
  "pad_token": "<pad>",
129
+ "pad_token_type_id": 0,
130
+ "padding_side": "right",
131
  "processor_class": "DonutProcessor",
132
  "sep_token": "</s>",
133
  "sp_model_kwargs": {},
134
+ "stride": 0,
135
  "tokenizer_class": "XLMRobertaTokenizer",
136
+ "truncation_side": "right",
137
+ "truncation_strategy": "longest_first",
138
  "unk_token": "<unk>"
139
  }