Hugging Face's logo

mychen76
/
invoice-and-receipts_donut_v1

Image-Text-to-Text
Transformers
PyTorch
Safetensors
vision-encoder-decoder
Inference Endpoints
Model card Files Community
3
mychen76 commited on
Commit
4c8fd50
•
1 Parent(s): 47b9a70

Training done

Browse files
Files changed (6) hide show
  1. added_tokens.json +76 -0
  2. preprocessor_config.json +26 -0
  3. sentencepiece.bpe.model +3 -0
  4. special_tokens_map.json +19 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +21 -0
added_tokens.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_None>": 57564,
3
+ "</s_client>": 57534,
4
+ "</s_client_tax_id>": 57538,
5
+ "</s_date>": 57572,
6
+ "</s_header>": 57526,
7
+ "</s_iban>": 57540,
8
+ "</s_ignore>": 57582,
9
+ "</s_invoice_date>": 57530,
10
+ "</s_invoice_no>": 57528,
11
+ "</s_item_desc>": 57544,
12
+ "</s_item_gross_worth>": 57554,
13
+ "</s_item_key>": 57588,
14
+ "</s_item_name>": 57590,
15
+ "</s_item_net_price>": 57548,
16
+ "</s_item_net_worth>": 57550,
17
+ "</s_item_qty>": 57546,
18
+ "</s_item_quantity>": 57594,
19
+ "</s_item_value>": 57592,
20
+ "</s_item_vat>": 57552,
21
+ "</s_items>": 57542,
22
+ "</s_line_items>": 57586,
23
+ "</s_seller>": 57532,
24
+ "</s_seller_tax_id>": 57536,
25
+ "</s_store_addr>": 57568,
26
+ "</s_store_name>": 57566,
27
+ "</s_subtotal>": 57576,
28
+ "</s_summary>": 57556,
29
+ "</s_tax>": 57578,
30
+ "</s_telephone>": 57570,
31
+ "</s_time>": 57574,
32
+ "</s_tips>": 57584,
33
+ "</s_total>": 57580,
34
+ "</s_total_gross_worth>": 57562,
35
+ "</s_total_net_worth>": 57558,
36
+ "</s_total_vat>": 57560,
37
+ "<s_None>": 57563,
38
+ "<s_client>": 57533,
39
+ "<s_client_tax_id>": 57537,
40
+ "<s_date>": 57571,
41
+ "<s_header>": 57525,
42
+ "<s_iban>": 57539,
43
+ "<s_ignore>": 57581,
44
+ "<s_iitcdip>": 57523,
45
+ "<s_invoice_date>": 57529,
46
+ "<s_invoice_no>": 57527,
47
+ "<s_item_desc>": 57543,
48
+ "<s_item_gross_worth>": 57553,
49
+ "<s_item_key>": 57587,
50
+ "<s_item_name>": 57589,
51
+ "<s_item_net_price>": 57547,
52
+ "<s_item_net_worth>": 57549,
53
+ "<s_item_qty>": 57545,
54
+ "<s_item_quantity>": 57593,
55
+ "<s_item_value>": 57591,
56
+ "<s_item_vat>": 57551,
57
+ "<s_items>": 57541,
58
+ "<s_line_items>": 57585,
59
+ "<s_receipt>": 57595,
60
+ "<s_seller>": 57531,
61
+ "<s_seller_tax_id>": 57535,
62
+ "<s_store_addr>": 57567,
63
+ "<s_store_name>": 57565,
64
+ "<s_subtotal>": 57575,
65
+ "<s_summary>": 57555,
66
+ "<s_synthdog>": 57524,
67
+ "<s_tax>": 57577,
68
+ "<s_telephone>": 57569,
69
+ "<s_time>": 57573,
70
+ "<s_tips>": 57583,
71
+ "<s_total>": 57579,
72
+ "<s_total_gross_worth>": 57561,
73
+ "<s_total_net_worth>": 57557,
74
+ "<s_total_vat>": 57559,
75
+ "<sep/>": 57522
76
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "DonutImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "DonutProcessor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": [
23
+ 960,
24
+ 1280
25
+ ]
26
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_iitcdip>",
4
+ "<s_synthdog>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "tokenizer_class": "XLMRobertaTokenizer",
20
+ "unk_token": "<unk>"
21
+ }