TomasFAV commited on
Commit
fd364bc
·
verified ·
1 Parent(s): e52cfdc

End of training

Browse files
Files changed (2) hide show
  1. processor_config.json +28 -0
  2. tokenizer_config.json +2 -45
processor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "apply_ocr": false,
4
+ "data_format": "channels_first",
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "LayoutLMv3ImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ },
27
+ "processor_class": "LayoutLMv3Processor"
28
+ }
tokenizer_config.json CHANGED
@@ -1,50 +1,8 @@
1
  {
2
  "add_prefix_space": true,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
  "apply_ocr": false,
 
46
  "bos_token": "<s>",
47
- "clean_up_tokenization_spaces": false,
48
  "cls_token": "<s>",
49
  "cls_token_box": [
50
  0,
@@ -54,7 +12,7 @@
54
  ],
55
  "eos_token": "</s>",
56
  "errors": "replace",
57
- "extra_special_tokens": {},
58
  "mask_token": "<mask>",
59
  "model_max_length": 512,
60
  "only_label_first_subword": true,
@@ -75,6 +33,5 @@
75
  0
76
  ],
77
  "tokenizer_class": "LayoutLMv3Tokenizer",
78
- "trim_offsets": true,
79
  "unk_token": "<unk>"
80
  }
 
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,
 
12
  ],
13
  "eos_token": "</s>",
14
  "errors": "replace",
15
+ "is_local": false,
16
  "mask_token": "<mask>",
17
  "model_max_length": 512,
18
  "only_label_first_subword": true,
 
33
  0
34
  ],
35
  "tokenizer_class": "LayoutLMv3Tokenizer",
 
36
  "unk_token": "<unk>"
37
  }