mkdigitalgmbh commited on
Commit
30e33b3
·
verified ·
1 Parent(s): f522508

Initialize model with custom labels and full weights

Browse files
config.json CHANGED
@@ -1,10 +1,18 @@
1
  {
2
- "_name_or_path": "microsoft/layoutlmv3-base",
3
  "architectures": [
4
  "LayoutLMv3ForTokenClassification"
5
  ],
6
- "model_type": "layoutlmv3",
7
- "num_labels": 19,
 
 
 
 
 
 
 
 
 
8
  "id2label": {
9
  "0": "O",
10
  "1": "B-MerchantName",
@@ -26,35 +34,48 @@
26
  "17": "B-LineItems",
27
  "18": "I-LineItems"
28
  },
 
 
 
29
  "label2id": {
30
- "O": 0,
31
- "B-MerchantName": 1,
32
- "I-MerchantName": 2,
33
- "B-MerchantAddress": 3,
34
- "I-MerchantAddress": 4,
35
- "B-TransactionDate": 5,
36
- "I-TransactionDate": 6,
37
  "B-Currency": 7,
38
- "I-Currency": 8,
 
 
 
 
39
  "B-Total": 9,
40
- "I-Total": 10,
41
  "B-TotalTax": 11,
42
- "I-TotalTax": 12,
43
- "B-InvoiceNumber": 13,
44
  "I-InvoiceNumber": 14,
45
- "B-Subtotal": 15,
 
 
46
  "I-Subtotal": 16,
47
- "B-LineItems": 17,
48
- "I-LineItems": 18
 
 
49
  },
50
- "coordinate_size": 1024,
51
- "hidden_size": 768,
52
- "image_size": 224,
53
- "input_size": 224,
54
- "intermediate_size": 3072,
55
  "max_2d_position_embeddings": 1024,
56
  "max_position_embeddings": 514,
 
 
 
57
  "num_attention_heads": 12,
 
58
  "num_hidden_layers": 12,
 
 
 
 
 
 
 
 
 
 
59
  "vocab_size": 50265
60
- }
 
1
  {
 
2
  "architectures": [
3
  "LayoutLMv3ForTokenClassification"
4
  ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "coordinate_size": 128,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "has_relative_attention_bias": true,
12
+ "has_spatial_attention_bias": true,
13
+ "hidden_act": "gelu",
14
+ "hidden_dropout_prob": 0.1,
15
+ "hidden_size": 768,
16
  "id2label": {
17
  "0": "O",
18
  "1": "B-MerchantName",
 
34
  "17": "B-LineItems",
35
  "18": "I-LineItems"
36
  },
37
+ "initializer_range": 0.02,
38
+ "input_size": 224,
39
+ "intermediate_size": 3072,
40
  "label2id": {
 
 
 
 
 
 
 
41
  "B-Currency": 7,
42
+ "B-InvoiceNumber": 13,
43
+ "B-LineItems": 17,
44
+ "B-MerchantAddress": 3,
45
+ "B-MerchantName": 1,
46
+ "B-Subtotal": 15,
47
  "B-Total": 9,
 
48
  "B-TotalTax": 11,
49
+ "B-TransactionDate": 5,
50
+ "I-Currency": 8,
51
  "I-InvoiceNumber": 14,
52
+ "I-LineItems": 18,
53
+ "I-MerchantAddress": 4,
54
+ "I-MerchantName": 2,
55
  "I-Subtotal": 16,
56
+ "I-Total": 10,
57
+ "I-TotalTax": 12,
58
+ "I-TransactionDate": 6,
59
+ "O": 0
60
  },
61
+ "layer_norm_eps": 1e-05,
 
 
 
 
62
  "max_2d_position_embeddings": 1024,
63
  "max_position_embeddings": 514,
64
+ "max_rel_2d_pos": 256,
65
+ "max_rel_pos": 128,
66
+ "model_type": "layoutlmv3",
67
  "num_attention_heads": 12,
68
+ "num_channels": 3,
69
  "num_hidden_layers": 12,
70
+ "pad_token_id": 1,
71
+ "patch_size": 16,
72
+ "rel_2d_pos_bins": 64,
73
+ "rel_pos_bins": 32,
74
+ "second_input_size": 112,
75
+ "shape_size": 128,
76
+ "text_embed": true,
77
+ "transformers_version": "4.57.1",
78
+ "type_vocab_size": 1,
79
+ "visual_embed": true,
80
  "vocab_size": 50265
81
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da092b4a57e2b5e715399be15f74104288631ded0787482cd646d1453eac1c48
3
+ size 503755044
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": "LayoutLMv3ImageProcessor",
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 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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,
51
+ 0,
52
+ 0,
53
+ 0
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,
61
+ "pad_token": "<pad>",
62
+ "pad_token_box": [
63
+ 0,
64
+ 0,
65
+ 0,
66
+ 0
67
+ ],
68
+ "pad_token_label": -100,
69
+ "processor_class": "LayoutLMv3Processor",
70
+ "sep_token": "</s>",
71
+ "sep_token_box": [
72
+ 0,
73
+ 0,
74
+ 0,
75
+ 0
76
+ ],
77
+ "tokenizer_class": "LayoutLMv3Tokenizer",
78
+ "trim_offsets": true,
79
+ "unk_token": "<unk>"
80
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff