bmpipli commited on
Commit
78d35d2
1 Parent(s): c00e846

Upload 11 files

Browse files
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "cess_amount",
18
+ "1": "cgst_amount",
19
+ "2": "customer_phone_number",
20
+ "3": "receipt_number",
21
+ "4": "savings",
22
+ "5": "sgst_amount",
23
+ "6": "sub_total_amount",
24
+ "7": "total_amount",
25
+ "8": "total_items_number",
26
+ "9": "transaction_date",
27
+ "10": "transaction_time",
28
+ "11": "vendor_address",
29
+ "12": "vendor_gst",
30
+ "13": "vendor_name",
31
+ "14": "vendor_phone_number",
32
+ "15": "Other"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "input_size": 224,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "Other": 15,
39
+ "cess_amount": 0,
40
+ "cgst_amount": 1,
41
+ "customer_phone_number": 2,
42
+ "receipt_number": 3,
43
+ "savings": 4,
44
+ "sgst_amount": 5,
45
+ "sub_total_amount": 6,
46
+ "total_amount": 7,
47
+ "total_items_number": 8,
48
+ "transaction_date": 9,
49
+ "transaction_time": 10,
50
+ "vendor_address": 11,
51
+ "vendor_gst": 12,
52
+ "vendor_name": 13,
53
+ "vendor_phone_number": 14
54
+ },
55
+ "layer_norm_eps": 1e-05,
56
+ "max_2d_position_embeddings": 1024,
57
+ "max_position_embeddings": 514,
58
+ "max_rel_2d_pos": 256,
59
+ "max_rel_pos": 128,
60
+ "model_type": "layoutlmv3",
61
+ "num_attention_heads": 12,
62
+ "num_channels": 3,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 1,
65
+ "patch_size": 16,
66
+ "rel_2d_pos_bins": 64,
67
+ "rel_pos_bins": 32,
68
+ "second_input_size": 112,
69
+ "shape_size": 128,
70
+ "text_embed": true,
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.25.0.dev0",
73
+ "type_vocab_size": 1,
74
+ "visual_embed": true,
75
+ "vocab_size": 50265
76
+ }
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
+ "feature_extractor_type": "LayoutLMv3ImageProcessor",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662d69013a25ab9f9c9926fa2b5750a4cc84898aec95ba2b7f5ce0635488431a
3
+ size 503796623
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e85a7e48da50ffb9b0464b4fda2dac5f7e2e0abd136a2a50f454b954cbc5c6a
3
+ size 14503
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 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_normalize": true,
27
+ "eos_token": {
28
+ "__type": "AddedToken",
29
+ "content": "</s>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "errors": "replace",
36
+ "mask_token": {
37
+ "__type": "AddedToken",
38
+ "content": "<mask>",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "model_max_length": 512,
45
+ "name_or_path": "microsoft/layoutlmv3-base",
46
+ "only_label_first_subword": true,
47
+ "pad_token": {
48
+ "__type": "AddedToken",
49
+ "content": "<pad>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "pad_token_box": [
56
+ 0,
57
+ 0,
58
+ 0,
59
+ 0
60
+ ],
61
+ "pad_token_label": -100,
62
+ "processor_class": "LayoutLMv3Processor",
63
+ "sep_token": {
64
+ "__type": "AddedToken",
65
+ "content": "</s>",
66
+ "lstrip": false,
67
+ "normalized": true,
68
+ "rstrip": false,
69
+ "single_word": false
70
+ },
71
+ "sep_token_box": [
72
+ 0,
73
+ 0,
74
+ 0,
75
+ 0
76
+ ],
77
+ "special_tokens_map_file": null,
78
+ "tokenizer_class": "LayoutLMv3Tokenizer",
79
+ "trim_offsets": true,
80
+ "unk_token": {
81
+ "__type": "AddedToken",
82
+ "content": "<unk>",
83
+ "lstrip": false,
84
+ "normalized": true,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ }
88
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af37770897643a6e424ad9913f0a6d7e2e9d0a0bf16c8c3109724ca6cd36179
3
+ size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff