wazzywazzywazzy commited on
Commit
6ea2617
1 Parent(s): ac8ddc9

layoutlmv3-finetune-invoice-3

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/layoutlmv3-base",
3
+ "architectures": [
4
+ "LayoutLMv3ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "coordinate_size": 128,
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": "STATE",
18
+ "1": "AMOUNT",
19
+ "2": "QUANTITY_INVOICED",
20
+ "3": "CITY",
21
+ "4": "VENDOR_NAME",
22
+ "5": "PO_NUMBER",
23
+ "6": "GL_DATE",
24
+ "7": "DESCRIPTION",
25
+ "8": "UNIT_PRICE",
26
+ "9": "O",
27
+ "10": "INVENTORY_ITEM_ID",
28
+ "11": "ZIP",
29
+ "12": "INVOICE_NUM",
30
+ "13": "ADDRESS_LINE1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "input_size": 224,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "ADDRESS_LINE1": 13,
37
+ "AMOUNT": 1,
38
+ "CITY": 3,
39
+ "DESCRIPTION": 7,
40
+ "GL_DATE": 6,
41
+ "INVENTORY_ITEM_ID": 10,
42
+ "INVOICE_NUM": 12,
43
+ "O": 9,
44
+ "PO_NUMBER": 5,
45
+ "QUANTITY_INVOICED": 2,
46
+ "STATE": 0,
47
+ "UNIT_PRICE": 8,
48
+ "VENDOR_NAME": 4,
49
+ "ZIP": 11
50
+ },
51
+ "layer_norm_eps": 1e-05,
52
+ "max_2d_position_embeddings": 1024,
53
+ "max_position_embeddings": 514,
54
+ "max_rel_2d_pos": 256,
55
+ "max_rel_pos": 128,
56
+ "model_type": "layoutlmv3",
57
+ "num_attention_heads": 12,
58
+ "num_channels": 3,
59
+ "num_hidden_layers": 12,
60
+ "pad_token_id": 1,
61
+ "patch_size": 16,
62
+ "rel_2d_pos_bins": 64,
63
+ "rel_pos_bins": 32,
64
+ "second_input_size": 112,
65
+ "shape_size": 128,
66
+ "text_embed": true,
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.27.4",
69
+ "type_vocab_size": 1,
70
+ "visual_embed": true,
71
+ "vocab_size": 50265
72
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": false,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "LayoutLMv3FeatureExtractor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "LayoutLMv3ImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "ocr_lang": null,
19
+ "processor_class": "LayoutLMv3Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "height": 224,
24
+ "width": 224
25
+ },
26
+ "tesseract_config": ""
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0f1c68348a18064eac287abbc9ab8c98989dac4ce493fff9d5bab2f94e1c74
3
+ size 503792305
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 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "apply_ocr": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "cls_token_box": [
21
+ 0,
22
+ 0,
23
+ 0,
24
+ 0
25
+ ],
26
+ "eos_token": {
27
+ "__type": "AddedToken",
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "errors": "replace",
35
+ "mask_token": {
36
+ "__type": "AddedToken",
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ },
43
+ "model_max_length": 512,
44
+ "only_label_first_subword": true,
45
+ "pad_token": {
46
+ "__type": "AddedToken",
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token_box": [
54
+ 0,
55
+ 0,
56
+ 0,
57
+ 0
58
+ ],
59
+ "pad_token_label": -100,
60
+ "processor_class": "LayoutLMv3Processor",
61
+ "sep_token": {
62
+ "__type": "AddedToken",
63
+ "content": "</s>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false
68
+ },
69
+ "sep_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "special_tokens_map_file": null,
76
+ "tokenizer_class": "LayoutLMv3Tokenizer",
77
+ "trim_offsets": true,
78
+ "unk_token": {
79
+ "__type": "AddedToken",
80
+ "content": "<unk>",
81
+ "lstrip": false,
82
+ "normalized": true,
83
+ "rstrip": false,
84
+ "single_word": false
85
+ }
86
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54eb3e70f9f94c27e4788126202078735af54ebd9a91fa4625384694b64e8239
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff