HasanALhomsi commited on
Commit
c377008
·
verified ·
1 Parent(s): f2c5b68

Upload processor

Browse files
Files changed (3) hide show
  1. processor_config.json +27 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +38 -0
processor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "apply_ocr": false,
4
+ "do_normalize": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ },
26
+ "processor_class": "LayoutLMv3Processor"
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "apply_ocr": false,
4
+ "backend": "tokenizers",
5
+ "bos_token": "<s>",
6
+ "cls_token": "<s>",
7
+ "cls_token_box": [
8
+ 0,
9
+ 0,
10
+ 0,
11
+ 0
12
+ ],
13
+ "eos_token": "</s>",
14
+ "errors": "replace",
15
+ "is_local": false,
16
+ "local_files_only": false,
17
+ "mask_token": "<mask>",
18
+ "model_max_length": 512,
19
+ "only_label_first_subword": true,
20
+ "pad_token": "<pad>",
21
+ "pad_token_box": [
22
+ 0,
23
+ 0,
24
+ 0,
25
+ 0
26
+ ],
27
+ "pad_token_label": -100,
28
+ "processor_class": "LayoutLMv3Processor",
29
+ "sep_token": "</s>",
30
+ "sep_token_box": [
31
+ 0,
32
+ 0,
33
+ 0,
34
+ 0
35
+ ],
36
+ "tokenizer_class": "LayoutLMv3Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }