Hugging Face's logo

cor-c
/
layoutlm-cord-tf

Token Classification
Transformers
TensorFlow
layoutlm
generated_from_keras_callback
Inference Endpoints
Model card Files Community
cor-c commited on
Commit
2b03620
•
1 Parent(s): 197c62e

Upload processor

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. preprocessor_config.json +25 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +80 -0
  6. vocab.txt +0 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: microsoft/layoutlm-base-uncased
4
  tags:
5
  - generated_from_keras_callback
 
6
  model-index:
7
  - name: layoutlm-cord-tf
8
  results: []
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_keras_callback
5
+ base_model: microsoft/layoutlm-base-uncased
6
  model-index:
7
  - name: layoutlm-cord-tf
8
  results: []
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "apply_ocr",
8
+ "ocr_lang",
9
+ "tesseract_config",
10
+ "return_tensors",
11
+ "data_format",
12
+ "input_data_format"
13
+ ],
14
+ "apply_ocr": true,
15
+ "do_resize": true,
16
+ "image_processor_type": "LayoutLMv2ImageProcessor",
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv2Processor",
19
+ "resample": 2,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "apply_ocr": false,
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "cls_token_box": [
49
+ 0,
50
+ 0,
51
+ 0,
52
+ 0
53
+ ],
54
+ "do_basic_tokenize": true,
55
+ "do_lower_case": true,
56
+ "mask_token": "[MASK]",
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "only_label_first_subword": true,
60
+ "pad_token": "[PAD]",
61
+ "pad_token_box": [
62
+ 0,
63
+ 0,
64
+ 0,
65
+ 0
66
+ ],
67
+ "pad_token_label": -100,
68
+ "processor_class": "LayoutLMv2Processor",
69
+ "sep_token": "[SEP]",
70
+ "sep_token_box": [
71
+ 1000,
72
+ 1000,
73
+ 1000,
74
+ 1000
75
+ ],
76
+ "strip_accents": null,
77
+ "tokenize_chinese_chars": true,
78
+ "tokenizer_class": "LayoutLMv2Tokenizer",
79
+ "unk_token": "[UNK]"
80
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff