afigini-digi commited on
Commit
529a695
1 Parent(s): 140b414

Training done

Browse files
added_tokens.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_billing_additional_info>": 57538,
3
+ "</s_company_address>": 57534,
4
+ "</s_company_name>": 57532,
5
+ "</s_company_vat_code>": 57536,
6
+ "</s_gross_total>": 57572,
7
+ "</s_gross_total_document>": 57584,
8
+ "</s_header>": 57526,
9
+ "</s_invoice_date>": 57546,
10
+ "</s_invoice_no>": 57544,
11
+ "</s_item_discount>": 57564,
12
+ "</s_item_gross_total>": 57566,
13
+ "</s_item_quantity>": 57560,
14
+ "</s_item_unit_price_standard>": 57562,
15
+ "</s_items>": 57552,
16
+ "</s_name>": 57576,
17
+ "</s_net_total>": 57578,
18
+ "</s_order_id>": 57548,
19
+ "</s_person_fiscal_address>": 57530,
20
+ "</s_person_fiscal_company>": 57528,
21
+ "</s_product_code>": 57554,
22
+ "</s_product_name>": 57556,
23
+ "</s_shipping_address>": 57542,
24
+ "</s_tax_pct>": 57568,
25
+ "</s_tax_total>": 57582,
26
+ "</s_taxable_total>": 57574,
27
+ "</s_total>": 57580,
28
+ "</s_um>": 57558,
29
+ "</s_user_vat_code>": 57550,
30
+ "</s_vat_summary>": 57570,
31
+ "</s_warehouse_address>": 57540,
32
+ "<s_billing_additional_info>": 57537,
33
+ "<s_company_address>": 57533,
34
+ "<s_company_name>": 57531,
35
+ "<s_company_vat_code>": 57535,
36
+ "<s_cord-v2>": 57585,
37
+ "<s_gross_total>": 57571,
38
+ "<s_gross_total_document>": 57583,
39
+ "<s_header>": 57525,
40
+ "<s_iitcdip>": 57523,
41
+ "<s_invoice_date>": 57545,
42
+ "<s_invoice_no>": 57543,
43
+ "<s_item_discount>": 57563,
44
+ "<s_item_gross_total>": 57565,
45
+ "<s_item_quantity>": 57559,
46
+ "<s_item_unit_price_standard>": 57561,
47
+ "<s_items>": 57551,
48
+ "<s_name>": 57575,
49
+ "<s_net_total>": 57577,
50
+ "<s_order_id>": 57547,
51
+ "<s_person_fiscal_address>": 57529,
52
+ "<s_person_fiscal_company>": 57527,
53
+ "<s_product_code>": 57553,
54
+ "<s_product_name>": 57555,
55
+ "<s_shipping_address>": 57541,
56
+ "<s_synthdog>": 57524,
57
+ "<s_tax_pct>": 57567,
58
+ "<s_tax_total>": 57581,
59
+ "<s_taxable_total>": 57573,
60
+ "<s_total>": 57579,
61
+ "<s_um>": 57557,
62
+ "<s_user_vat_code>": 57549,
63
+ "<s_vat_summary>": 57569,
64
+ "<s_warehouse_address>": 57539,
65
+ "<sep/>": 57522
66
+ }
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 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "naver-clova-ix/donut-base",
15
+ "pad_token": "<pad>",
16
+ "processor_class": "DonutProcessor",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "XLMRobertaTokenizer",
21
+ "unk_token": "<unk>"
22
+ }