Training done
Browse files- added_tokens.json +100 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
added_tokens.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_box_no>": 57603,
|
3 |
+
"</s_customer>": 57550,
|
4 |
+
"</s_customer_address>": 57554,
|
5 |
+
"</s_customer_contact_person>": 57597,
|
6 |
+
"</s_customer_email>": 57572,
|
7 |
+
"</s_customer_name>": 57552,
|
8 |
+
"</s_customer_no>": 57595,
|
9 |
+
"</s_customer_phone_no>": 57570,
|
10 |
+
"</s_customer_pin>": 57556,
|
11 |
+
"</s_customer_reference_no>": 57609,
|
12 |
+
"</s_cutomer_no>": 57599,
|
13 |
+
"</s_date>": 57530,
|
14 |
+
"</s_delivery_contact>": 57568,
|
15 |
+
"</s_delivery_contact_person>": 57619,
|
16 |
+
"</s_delivery_note_no>": 57574,
|
17 |
+
"</s_dnote_no>": 57532,
|
18 |
+
"</s_document_no>": 57593,
|
19 |
+
"</s_document_type>": 57528,
|
20 |
+
"</s_dropoff point>": 57590,
|
21 |
+
"</s_dropoff_point>": 57548,
|
22 |
+
"</s_header>": 57526,
|
23 |
+
"</s_invoice_no>": 57576,
|
24 |
+
"</s_item36s>": 57605,
|
25 |
+
"</s_item_batch>": 57617,
|
26 |
+
"</s_item_code>": 57584,
|
27 |
+
"</s_item_description>": 57560,
|
28 |
+
"</s_item_quantity>": 57562,
|
29 |
+
"</s_item_total_price>": 57566,
|
30 |
+
"</s_item_unit_price>": 57564,
|
31 |
+
"</s_item_weight>": 57588,
|
32 |
+
"</s_items>": 57558,
|
33 |
+
"</s_items_total_price>": 57578,
|
34 |
+
"</s_lpo_no>": 57586,
|
35 |
+
"</s_order_no>": 57580,
|
36 |
+
"</s_packing_list_no>": 57601,
|
37 |
+
"</s_po_no>": 57582,
|
38 |
+
"</s_reference_no>": 57534,
|
39 |
+
"</s_shipper>": 57536,
|
40 |
+
"</s_shipper_address>": 57540,
|
41 |
+
"</s_shipper_email>": 57544,
|
42 |
+
"</s_shipper_name>": 57538,
|
43 |
+
"</s_shipper_phone_no>": 57542,
|
44 |
+
"</s_shipper_pin>": 57546,
|
45 |
+
"</s_shipping_date>": 57607,
|
46 |
+
"</s_source>": 57611,
|
47 |
+
"</s_source_no>": 57613,
|
48 |
+
"</s_total_weight>": 57615,
|
49 |
+
"<s_box_no>": 57602,
|
50 |
+
"<s_cord-v2>": 57591,
|
51 |
+
"<s_customer>": 57549,
|
52 |
+
"<s_customer_address>": 57553,
|
53 |
+
"<s_customer_contact_person>": 57596,
|
54 |
+
"<s_customer_email>": 57571,
|
55 |
+
"<s_customer_name>": 57551,
|
56 |
+
"<s_customer_no>": 57594,
|
57 |
+
"<s_customer_phone_no>": 57569,
|
58 |
+
"<s_customer_pin>": 57555,
|
59 |
+
"<s_customer_reference_no>": 57608,
|
60 |
+
"<s_cutomer_no>": 57598,
|
61 |
+
"<s_date>": 57529,
|
62 |
+
"<s_delivery_contact>": 57567,
|
63 |
+
"<s_delivery_contact_person>": 57618,
|
64 |
+
"<s_delivery_note_no>": 57573,
|
65 |
+
"<s_dnote_no>": 57531,
|
66 |
+
"<s_document_no>": 57592,
|
67 |
+
"<s_document_type>": 57527,
|
68 |
+
"<s_dropoff point>": 57589,
|
69 |
+
"<s_dropoff_point>": 57547,
|
70 |
+
"<s_header>": 57525,
|
71 |
+
"<s_iitcdip>": 57523,
|
72 |
+
"<s_invoice_no>": 57575,
|
73 |
+
"<s_item36s>": 57604,
|
74 |
+
"<s_item_batch>": 57616,
|
75 |
+
"<s_item_code>": 57583,
|
76 |
+
"<s_item_description>": 57559,
|
77 |
+
"<s_item_quantity>": 57561,
|
78 |
+
"<s_item_total_price>": 57565,
|
79 |
+
"<s_item_unit_price>": 57563,
|
80 |
+
"<s_item_weight>": 57587,
|
81 |
+
"<s_items>": 57557,
|
82 |
+
"<s_items_total_price>": 57577,
|
83 |
+
"<s_lpo_no>": 57585,
|
84 |
+
"<s_order_no>": 57579,
|
85 |
+
"<s_packing_list_no>": 57600,
|
86 |
+
"<s_po_no>": 57581,
|
87 |
+
"<s_reference_no>": 57533,
|
88 |
+
"<s_shipper>": 57535,
|
89 |
+
"<s_shipper_address>": 57539,
|
90 |
+
"<s_shipper_email>": 57543,
|
91 |
+
"<s_shipper_name>": 57537,
|
92 |
+
"<s_shipper_phone_no>": 57541,
|
93 |
+
"<s_shipper_pin>": 57545,
|
94 |
+
"<s_shipping_date>": 57606,
|
95 |
+
"<s_source>": 57610,
|
96 |
+
"<s_source_no>": 57612,
|
97 |
+
"<s_synthdog>": 57524,
|
98 |
+
"<s_total_weight>": 57614,
|
99 |
+
"<sep/>": 57522
|
100 |
+
}
|
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 |
+
}
|