Upload 9 files
Browse files- config.json +66 -0
- merges.txt +0 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Caption",
|
18 |
+
"1": "Footnote",
|
19 |
+
"2": "Formula",
|
20 |
+
"3": "List-item",
|
21 |
+
"4": "Page-footer",
|
22 |
+
"5": "Page-header",
|
23 |
+
"6": "Picture",
|
24 |
+
"7": "Section-header",
|
25 |
+
"8": "Table",
|
26 |
+
"9": "Text",
|
27 |
+
"10": "Title"
|
28 |
+
},
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"input_size": 224,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"Caption": 0,
|
34 |
+
"Footnote": 1,
|
35 |
+
"Formula": 2,
|
36 |
+
"List-item": 3,
|
37 |
+
"Page-footer": 4,
|
38 |
+
"Page-header": 5,
|
39 |
+
"Picture": 6,
|
40 |
+
"Section-header": 7,
|
41 |
+
"Table": 8,
|
42 |
+
"Text": 9,
|
43 |
+
"Title": 10
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-05,
|
46 |
+
"max_2d_position_embeddings": 1024,
|
47 |
+
"max_position_embeddings": 514,
|
48 |
+
"max_rel_2d_pos": 256,
|
49 |
+
"max_rel_pos": 128,
|
50 |
+
"model_type": "layoutlmv3",
|
51 |
+
"num_attention_heads": 12,
|
52 |
+
"num_channels": 3,
|
53 |
+
"num_hidden_layers": 12,
|
54 |
+
"pad_token_id": 1,
|
55 |
+
"patch_size": 16,
|
56 |
+
"rel_2d_pos_bins": 64,
|
57 |
+
"rel_pos_bins": 32,
|
58 |
+
"second_input_size": 112,
|
59 |
+
"shape_size": 128,
|
60 |
+
"text_embed": true,
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.33.3",
|
63 |
+
"type_vocab_size": 1,
|
64 |
+
"visual_embed": true,
|
65 |
+
"vocab_size": 50265
|
66 |
+
}
|
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 sha256:070b9caa9ce6098cc858fb356271b0798eaaf92fed675b6bae5b842b930c3d9d
|
3 |
+
size 503776721
|
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 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token_box": [
|
22 |
+
0,
|
23 |
+
0,
|
24 |
+
0,
|
25 |
+
0
|
26 |
+
],
|
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 |
+
"only_label_first_subword": true,
|
46 |
+
"pad_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "<pad>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"pad_token_box": [
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0,
|
58 |
+
0
|
59 |
+
],
|
60 |
+
"pad_token_label": -100,
|
61 |
+
"processor_class": "LayoutLMv3Processor",
|
62 |
+
"sep_token": {
|
63 |
+
"__type": "AddedToken",
|
64 |
+
"content": "</s>",
|
65 |
+
"lstrip": false,
|
66 |
+
"normalized": true,
|
67 |
+
"rstrip": false,
|
68 |
+
"single_word": false
|
69 |
+
},
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
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 sha256:1e712442760e29987520b10807deb0ea15e5d603f4591ac5c9d4ce5850d43336
|
3 |
+
size 3951
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|