MuryTheReaper
commited on
Commit
•
66d9c67
1
Parent(s):
82717d5
layoutlmv3-finetuned-cord_gpu
Browse files- README.md +52 -0
- config.json +90 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +43 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +79 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: microsoft/layoutlmv3-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: layoutlmv3-finetuned-cord_gpu
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# layoutlmv3-finetuned-cord_gpu
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 1e-05
|
36 |
+
- train_batch_size: 5
|
37 |
+
- eval_batch_size: 5
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- training_steps: 10
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.40.1
|
50 |
+
- Pytorch 2.3.0+cpu
|
51 |
+
- Datasets 2.19.0
|
52 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "O",
|
18 |
+
"1": "I-menu.cnt",
|
19 |
+
"2": "I-menu.discountprice",
|
20 |
+
"3": "I-menu.nm",
|
21 |
+
"4": "I-menu.num",
|
22 |
+
"5": "I-menu.price",
|
23 |
+
"6": "I-menu.sub_cnt",
|
24 |
+
"7": "I-menu.sub_nm",
|
25 |
+
"8": "I-menu.sub_price",
|
26 |
+
"9": "I-menu.unitprice",
|
27 |
+
"10": "I-sub_total.discount_price",
|
28 |
+
"11": "I-sub_total.etc",
|
29 |
+
"12": "I-sub_total.service_price",
|
30 |
+
"13": "I-sub_total.subtotal_price",
|
31 |
+
"14": "I-sub_total.tax_price",
|
32 |
+
"15": "I-total.cashprice",
|
33 |
+
"16": "I-total.changeprice",
|
34 |
+
"17": "I-total.creditcardprice",
|
35 |
+
"18": "I-total.emoneyprice",
|
36 |
+
"19": "I-total.menuqty_cnt",
|
37 |
+
"20": "I-total.menutype_cnt",
|
38 |
+
"21": "I-total.total_etc",
|
39 |
+
"22": "I-total.total_price"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"input_size": 224,
|
43 |
+
"intermediate_size": 3072,
|
44 |
+
"label2id": {
|
45 |
+
"I-menu.cnt": 1,
|
46 |
+
"I-menu.discountprice": 2,
|
47 |
+
"I-menu.nm": 3,
|
48 |
+
"I-menu.num": 4,
|
49 |
+
"I-menu.price": 5,
|
50 |
+
"I-menu.sub_cnt": 6,
|
51 |
+
"I-menu.sub_nm": 7,
|
52 |
+
"I-menu.sub_price": 8,
|
53 |
+
"I-menu.unitprice": 9,
|
54 |
+
"I-sub_total.discount_price": 10,
|
55 |
+
"I-sub_total.etc": 11,
|
56 |
+
"I-sub_total.service_price": 12,
|
57 |
+
"I-sub_total.subtotal_price": 13,
|
58 |
+
"I-sub_total.tax_price": 14,
|
59 |
+
"I-total.cashprice": 15,
|
60 |
+
"I-total.changeprice": 16,
|
61 |
+
"I-total.creditcardprice": 17,
|
62 |
+
"I-total.emoneyprice": 18,
|
63 |
+
"I-total.menuqty_cnt": 19,
|
64 |
+
"I-total.menutype_cnt": 20,
|
65 |
+
"I-total.total_etc": 21,
|
66 |
+
"I-total.total_price": 22,
|
67 |
+
"O": 0
|
68 |
+
},
|
69 |
+
"layer_norm_eps": 1e-05,
|
70 |
+
"max_2d_position_embeddings": 1024,
|
71 |
+
"max_position_embeddings": 514,
|
72 |
+
"max_rel_2d_pos": 256,
|
73 |
+
"max_rel_pos": 128,
|
74 |
+
"model_type": "layoutlmv3",
|
75 |
+
"num_attention_heads": 12,
|
76 |
+
"num_channels": 3,
|
77 |
+
"num_hidden_layers": 12,
|
78 |
+
"pad_token_id": 1,
|
79 |
+
"patch_size": 16,
|
80 |
+
"rel_2d_pos_bins": 64,
|
81 |
+
"rel_pos_bins": 32,
|
82 |
+
"second_input_size": 112,
|
83 |
+
"shape_size": 128,
|
84 |
+
"text_embed": true,
|
85 |
+
"torch_dtype": "float32",
|
86 |
+
"transformers_version": "4.40.1",
|
87 |
+
"type_vocab_size": 1,
|
88 |
+
"visual_embed": true,
|
89 |
+
"vocab_size": 50265
|
90 |
+
}
|
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:efa6d48c498915ce4918dc3877d6929eec617c0b43d8b589184ac692554bd55e
|
3 |
+
size 503767348
|
preprocessor_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"apply_ocr",
|
13 |
+
"ocr_lang",
|
14 |
+
"tesseract_config",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
+
"apply_ocr": false,
|
20 |
+
"do_normalize": true,
|
21 |
+
"do_rescale": true,
|
22 |
+
"do_resize": true,
|
23 |
+
"image_mean": [
|
24 |
+
0.5,
|
25 |
+
0.5,
|
26 |
+
0.5
|
27 |
+
],
|
28 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
29 |
+
"image_std": [
|
30 |
+
0.5,
|
31 |
+
0.5,
|
32 |
+
0.5
|
33 |
+
],
|
34 |
+
"ocr_lang": null,
|
35 |
+
"processor_class": "LayoutLMv3Processor",
|
36 |
+
"resample": 2,
|
37 |
+
"rescale_factor": 0.00392156862745098,
|
38 |
+
"size": {
|
39 |
+
"height": 224,
|
40 |
+
"width": 224
|
41 |
+
},
|
42 |
+
"tesseract_config": ""
|
43 |
+
}
|
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 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
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 |
+
"mask_token": "<mask>",
|
58 |
+
"model_max_length": 512,
|
59 |
+
"only_label_first_subword": true,
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"pad_token_box": [
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0,
|
65 |
+
0
|
66 |
+
],
|
67 |
+
"pad_token_label": -100,
|
68 |
+
"processor_class": "LayoutLMv3Processor",
|
69 |
+
"sep_token": "</s>",
|
70 |
+
"sep_token_box": [
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0,
|
74 |
+
0
|
75 |
+
],
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": "<unk>"
|
79 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1686913e292232bf4381b6f681bdcc6b7700c61e1a8c5692750f13d639a7daa1
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|