Hugging Face's logo

Digiquanta
/
Facesheet_classification

Text Classification
Transformers
Safetensors
layoutlmv3
Model card Files
xet
Community
Digiquanta commited on
Commit
6023c21
·
verified ·
1 Parent(s): 87076ea

added config files

Browse files
Files changed (7) hide show
  1. config.json +19 -5
  2. merges.txt +0 -0
  3. preprocessor_config.json +26 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +79 -0
  7. vocab.json +0 -0
config.json CHANGED
@@ -14,15 +14,29 @@
14
  "hidden_dropout_prob": 0.1,
15
  "hidden_size": 768,
16
  "id2label": {
17
- "0": "facesheet",
18
- "1": "other"
 
 
 
 
 
 
 
19
  },
20
  "initializer_range": 0.02,
21
  "input_size": 224,
22
  "intermediate_size": 3072,
23
  "label2id": {
24
- "facesheet": 0,
25
- "other": 1
 
 
 
 
 
 
 
26
  },
27
  "layer_norm_eps": 1e-05,
28
  "max_2d_position_embeddings": 1024,
@@ -41,7 +55,7 @@
41
  "shape_size": 128,
42
  "text_embed": true,
43
  "torch_dtype": "float32",
44
- "transformers_version": "4.47.1",
45
  "type_vocab_size": 1,
46
  "visual_embed": true,
47
  "vocab_size": 50265
 
14
  "hidden_dropout_prob": 0.1,
15
  "hidden_size": 768,
16
  "id2label": {
17
+ "0": "0",
18
+ "1": "1",
19
+ "2": "2",
20
+ "3": "3",
21
+ "4": "4",
22
+ "5": "5",
23
+ "6": "6",
24
+ "7": "7",
25
+ "8": "8"
26
  },
27
  "initializer_range": 0.02,
28
  "input_size": 224,
29
  "intermediate_size": 3072,
30
  "label2id": {
31
+ "0": 0,
32
+ "1": 1,
33
+ "2": 2,
34
+ "3": 3,
35
+ "4": 4,
36
+ "5": 5,
37
+ "6": 6,
38
+ "7": 7,
39
+ "8": 8
40
  },
41
  "layer_norm_eps": 1e-05,
42
  "max_2d_position_embeddings": 1024,
 
55
  "shape_size": 128,
56
  "text_embed": true,
57
  "torch_dtype": "float32",
58
+ "transformers_version": "4.47.0",
59
  "type_vocab_size": 1,
60
  "visual_embed": true,
61
  "vocab_size": 50265
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "LayoutLMv3FeatureExtractor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "ocr_lang": null,
18
+ "processor_class": "LayoutLMv3Processor",
19
+ "resample": 2,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": {
22
+ "height": 224,
23
+ "width": 224
24
+ },
25
+ "tesseract_config": ""
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "cls_token_box": [
49
+ 0,
50
+ 0,
51
+ 0,
52
+ 0
53
+ ],
54
+ "eos_token": "</s>",
55
+ "errors": "replace",
56
+ "extra_special_tokens": {},
57
+ "mask_token": "<mask>",
58
+ "model_max_length": 512,
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": "LayoutLMv3Processor",
69
+ "sep_token": "</s>",
70
+ "sep_token_box": [
71
+ 0,
72
+ 0,
73
+ 0,
74
+ 0
75
+ ],
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": "<unk>"
79
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff