Teaa314 commited on
Commit
0887319
·
verified ·
1 Parent(s): 8376c1d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-INVOICE_NUMBER",
19
+ "2": "I-INVOICE_NUMBER",
20
+ "3": "B-DATE",
21
+ "4": "I-DATE",
22
+ "5": "B-VENDOR_NAME",
23
+ "6": "I-VENDOR_NAME",
24
+ "7": "B-VENDOR_ADDRESS",
25
+ "8": "I-VENDOR_ADDRESS",
26
+ "9": "B-CUSTOMER_NAME",
27
+ "10": "I-CUSTOMER_NAME",
28
+ "11": "B-CUSTOMER_ADDRESS",
29
+ "12": "I-CUSTOMER_ADDRESS",
30
+ "13": "B-TOTAL_AMOUNT",
31
+ "14": "I-TOTAL_AMOUNT",
32
+ "15": "B-TAX_AMOUNT",
33
+ "16": "I-TAX_AMOUNT",
34
+ "17": "B-QUANTITY",
35
+ "18": "I-QUANTITY",
36
+ "19": "B-NET_PRICE",
37
+ "20": "I-NET_PRICE"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "input_size": 224,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "B-CUSTOMER_ADDRESS": 11,
44
+ "B-CUSTOMER_NAME": 9,
45
+ "B-DATE": 3,
46
+ "B-INVOICE_NUMBER": 1,
47
+ "B-NET_PRICE": 19,
48
+ "B-QUANTITY": 17,
49
+ "B-TAX_AMOUNT": 15,
50
+ "B-TOTAL_AMOUNT": 13,
51
+ "B-VENDOR_ADDRESS": 7,
52
+ "B-VENDOR_NAME": 5,
53
+ "I-CUSTOMER_ADDRESS": 12,
54
+ "I-CUSTOMER_NAME": 10,
55
+ "I-DATE": 4,
56
+ "I-INVOICE_NUMBER": 2,
57
+ "I-NET_PRICE": 20,
58
+ "I-QUANTITY": 18,
59
+ "I-TAX_AMOUNT": 16,
60
+ "I-TOTAL_AMOUNT": 14,
61
+ "I-VENDOR_ADDRESS": 8,
62
+ "I-VENDOR_NAME": 6,
63
+ "O": 0
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "max_2d_position_embeddings": 1024,
67
+ "max_position_embeddings": 514,
68
+ "max_rel_2d_pos": 256,
69
+ "max_rel_pos": 128,
70
+ "model_type": "layoutlmv3",
71
+ "num_attention_heads": 12,
72
+ "num_channels": 3,
73
+ "num_hidden_layers": 12,
74
+ "pad_token_id": 1,
75
+ "patch_size": 16,
76
+ "rel_2d_pos_bins": 64,
77
+ "rel_pos_bins": 32,
78
+ "second_input_size": 112,
79
+ "shape_size": 128,
80
+ "text_embed": true,
81
+ "transformers_version": "4.57.3",
82
+ "type_vocab_size": 1,
83
+ "visual_embed": true,
84
+ "vocab_size": 50265
85
+ }
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 sha256:587d238e06c90f37c2256a998d78f29a1a71deefb3266e9c51f8f1ac289a2358
3
+ size 503761196
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef1c745a7d14d848839a322fb6bd32797e03b5685581d7e973bdf3d4f5c6053
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff