nassimb0u commited on
Commit
d9c5a75
·
verified ·
1 Parent(s): ac0f7d1

add initial model

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "“": 50265,
3
+ "”": 50266
4
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CustomLayoutLMv3ForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "coordinate_size": 128,
9
+ "eos_token_id": 2,
10
+ "has_relative_attention_bias": true,
11
+ "has_spatial_attention_bias": true,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "CHART_TITLE",
17
+ "1": "LEGEND_TITLE",
18
+ "2": "LEGEND_LABEL",
19
+ "3": "AXIS_TITLE",
20
+ "4": "TICK_LABEL",
21
+ "5": "TICK_GROUPING",
22
+ "6": "MARK_LABEL",
23
+ "7": "VALUE_LABEL",
24
+ "8": "OTHER"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "input_size": 224,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "AXIS_TITLE": 3,
31
+ "CHART_TITLE": 0,
32
+ "LEGEND_LABEL": 2,
33
+ "LEGEND_TITLE": 1,
34
+ "MARK_LABEL": 6,
35
+ "OTHER": 8,
36
+ "TICK_GROUPING": 5,
37
+ "TICK_LABEL": 4,
38
+ "VALUE_LABEL": 7
39
+ },
40
+ "layer_norm_eps": 1e-05,
41
+ "max_2d_position_embeddings": 1024,
42
+ "max_position_embeddings": 514,
43
+ "max_rel_2d_pos": 256,
44
+ "max_rel_pos": 128,
45
+ "model_type": "layoutlmv3",
46
+ "num_attention_heads": 12,
47
+ "num_channels": 3,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 1,
50
+ "patch_size": 16,
51
+ "rel_2d_pos_bins": 64,
52
+ "rel_pos_bins": 32,
53
+ "second_input_size": 112,
54
+ "shape_size": 128,
55
+ "text_embed": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.51.3",
58
+ "type_vocab_size": 1,
59
+ "visual_embed": true,
60
+ "vocab_size": 50267
61
+ }
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 sha256:4472c551128d70727b277607c970bae407d2acf84c5c0727a928a3419475462f
3
+ size 501367828
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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "“",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "”",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": true,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "cls_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "mask_token": {
40
+ "content": "<mask>",
41
+ "lstrip": true,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "pad_token": {
47
+ "content": "<pad>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "sep_token": {
54
+ "content": "</s>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "unk_token": {
61
+ "content": "<unk>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ }
67
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50265": {
45
+ "content": "“",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "”",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [
62
+ "“",
63
+ "”"
64
+ ],
65
+ "apply_ocr": false,
66
+ "bos_token": "<s>",
67
+ "clean_up_tokenization_spaces": false,
68
+ "cls_token": "<s>",
69
+ "cls_token_box": [
70
+ 0,
71
+ 0,
72
+ 0,
73
+ 0
74
+ ],
75
+ "eos_token": "</s>",
76
+ "errors": "replace",
77
+ "extra_special_tokens": {},
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 512,
80
+ "only_label_first_subword": true,
81
+ "pad_token": "<pad>",
82
+ "pad_token_box": [
83
+ 0,
84
+ 0,
85
+ 0,
86
+ 0
87
+ ],
88
+ "pad_token_label": -100,
89
+ "processor_class": "LayoutLMv3Processor",
90
+ "sep_token": "</s>",
91
+ "sep_token_box": [
92
+ 0,
93
+ 0,
94
+ 0,
95
+ 0
96
+ ],
97
+ "tokenizer_class": "LayoutLMv3Tokenizer",
98
+ "trim_offsets": true,
99
+ "unk_token": "<unk>"
100
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bee2580ef60e508678d9d998e049cb8203fc46e0027da7f8e98b83f17b7be8
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff