EpsilonGreedy commited on
Commit
8565e5c
·
verified ·
1 Parent(s): 588af32

Upload processor

Browse files
Files changed (3) hide show
  1. processor_config.json +31 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +21 -0
processor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "crop_size": {
4
+ "height": 224,
5
+ "width": 224
6
+ },
7
+ "data_format": "channels_first",
8
+ "do_center_crop": false,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "image_processor_type": "DeiTImageProcessorFast",
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 384,
27
+ "width": 384
28
+ }
29
+ },
30
+ "processor_class": "TrOCRProcessor"
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "extra_special_tokens": [
8
+ "<s>",
9
+ "</s>"
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
+ }