laverdes commited on
Commit
bf71343
1 Parent(s): 2b500f6

feat: upload missing files from backup

Browse files
added_tokens.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Address>": 57546,
3
+ "</s_Advertisement>": 57544,
4
+ "</s_Author>": 57552,
5
+ "</s_Caption>": 57558,
6
+ "</s_Chart>": 57560,
7
+ "</s_Field-Name>": 57542,
8
+ "</s_Footer>": 57548,
9
+ "</s_Header>": 57532,
10
+ "</s_Headline>": 57538,
11
+ "</s_Link>": 57554,
12
+ "</s_List-item>": 57536,
13
+ "</s_Metadata>": 57530,
14
+ "</s_Misc>": 57528,
15
+ "</s_Subheadline>": 57526,
16
+ "</s_Table>": 57556,
17
+ "</s_Text>": 57534,
18
+ "</s_Title>": 57550,
19
+ "</s_Value>": 57540,
20
+ "<s_Address>": 57545,
21
+ "<s_Advertisement>": 57543,
22
+ "<s_Author>": 57551,
23
+ "<s_Caption>": 57557,
24
+ "<s_Chart>": 57559,
25
+ "<s_Field-Name>": 57541,
26
+ "<s_Footer>": 57547,
27
+ "<s_Header>": 57531,
28
+ "<s_Headline>": 57537,
29
+ "<s_Link>": 57553,
30
+ "<s_List-item>": 57535,
31
+ "<s_Metadata>": 57529,
32
+ "<s_Misc>": 57527,
33
+ "<s_Subheadline>": 57525,
34
+ "<s_Table>": 57555,
35
+ "<s_Text>": 57533,
36
+ "<s_Title>": 57549,
37
+ "<s_Value>": 57539,
38
+ "<s_iitcdip>": 57523,
39
+ "<s_synthdog>": 57524,
40
+ "<sep/>": 57522
41
+ }
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
+ 720,
24
+ 960
25
+ ]
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_Subheadline>",
4
+ "</s_Subheadline>",
5
+ "<s_Misc>",
6
+ "</s_Misc>",
7
+ "<s_Metadata>",
8
+ "</s_Metadata>",
9
+ "<s_Header>",
10
+ "</s_Header>",
11
+ "<s_Text>",
12
+ "</s_Text>",
13
+ "<s_List-item>",
14
+ "</s_List-item>",
15
+ "<s_Headline>",
16
+ "</s_Headline>",
17
+ "<s_Value>",
18
+ "</s_Value>",
19
+ "<s_Field-Name>",
20
+ "</s_Field-Name>",
21
+ "<s_Advertisement>",
22
+ "</s_Advertisement>",
23
+ "<s_Address>",
24
+ "</s_Address>",
25
+ "<s_Footer>",
26
+ "</s_Footer>",
27
+ "<s_Title>",
28
+ "</s_Title>",
29
+ "<s_Author>",
30
+ "</s_Author>",
31
+ "<s_Link>",
32
+ "</s_Link>",
33
+ "<s_Table>",
34
+ "</s_Table>",
35
+ "<s_Caption>",
36
+ "</s_Caption>",
37
+ "<s_Chart>",
38
+ "</s_Chart>",
39
+ "<s>",
40
+ "</s>"
41
+ ],
42
+ "bos_token": "<s>",
43
+ "cls_token": "<s>",
44
+ "eos_token": "</s>",
45
+ "mask_token": {
46
+ "content": "<mask>",
47
+ "lstrip": true,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "unk_token": "<unk>"
55
+ }
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
+ }