iliabel commited on
Commit
780d2bd
1 Parent(s): 852519e

Upload processor

Browse files
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "LayoutLMv2FeatureExtractor",
5
+ "image_processor_type": "LayoutLMv2ImageProcessor",
6
+ "ocr_lang": null,
7
+ "processor_class": "LayoutLMv2Processor",
8
+ "resample": 2,
9
+ "size": {
10
+ "height": 224,
11
+ "width": 224
12
+ },
13
+ "tesseract_config": ""
14
+ }
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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "cls_token_box": [
48
+ 0,
49
+ 0,
50
+ 0,
51
+ 0
52
+ ],
53
+ "do_basic_tokenize": true,
54
+ "do_lower_case": true,
55
+ "mask_token": "[MASK]",
56
+ "max_length": 512,
57
+ "model_max_length": 512,
58
+ "never_split": null,
59
+ "only_label_first_subword": true,
60
+ "pad_to_multiple_of": null,
61
+ "pad_token": "[PAD]",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
69
+ "pad_token_type_id": 0,
70
+ "padding_side": "right",
71
+ "processor_class": "LayoutLMv2Processor",
72
+ "sep_token": "[SEP]",
73
+ "sep_token_box": [
74
+ 1000,
75
+ 1000,
76
+ 1000,
77
+ 1000
78
+ ],
79
+ "stride": 0,
80
+ "strip_accents": null,
81
+ "tokenize_chinese_chars": true,
82
+ "tokenizer_class": "LayoutLMv2Tokenizer",
83
+ "truncation_side": "right",
84
+ "truncation_strategy": "longest_first",
85
+ "unk_token": "[UNK]"
86
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff