TomasFAV commited on
Commit
d3a60e0
·
verified ·
1 Parent(s): 084afc3

Upload processor

Browse files
Files changed (3) hide show
  1. processor_config.json +19 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +45 -0
processor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "image_processor_type": "Pix2StructImageProcessorFast",
7
+ "is_vqa": true,
8
+ "max_patches": 2048,
9
+ "patch_size": {
10
+ "height": 16,
11
+ "width": 16
12
+ },
13
+ "size": {
14
+ "height": 2338,
15
+ "width": 1654
16
+ }
17
+ },
18
+ "processor_class": "Pix2StructProcessor"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "eos_token": "</s>",
4
+ "extra_ids": 100,
5
+ "extra_special_tokens": [
6
+ "</s_supp_tax_id>",
7
+ "<s_bic>",
8
+ "<s_const_symbol>",
9
+ "</s_due_date>",
10
+ "</s_total>",
11
+ "</s_invoice_number>",
12
+ "</s_const_symbol>",
13
+ "<s_supp_tax_id>",
14
+ "<s_supp_register_id>",
15
+ "<s_total>",
16
+ "<s_payment_type>",
17
+ "</s_bank_account_number>",
18
+ "<s_variable_symbol>",
19
+ "</s_iban>",
20
+ "</s_taxable_supply_date>",
21
+ "</s_issue_date>",
22
+ "</s_cust_tax_id>",
23
+ "</s_variable_symbol>",
24
+ "<s_cust_tax_id>",
25
+ "<s_cust_register_id>",
26
+ "</s_cust_register_id>",
27
+ "</s_bic>",
28
+ "</s_payment_type>",
29
+ "</s_supp_register_id>",
30
+ "<s_taxable_supply_date>",
31
+ "<s_due_date>",
32
+ "<s_iban>",
33
+ "<s_invoice_number>",
34
+ "<s_issue_date>",
35
+ "<s_bank_account_number>"
36
+ ],
37
+ "is_local": true,
38
+ "is_vqa": true,
39
+ "model_max_length": 1000000000000000019884624838656,
40
+ "pad_token": "<pad>",
41
+ "processor_class": "Pix2StructProcessor",
42
+ "sp_model_kwargs": {},
43
+ "tokenizer_class": "T5Tokenizer",
44
+ "unk_token": "<unk>"
45
+ }