Hugging Face's logo

dasomoh88
/
Donut_KCI_v3.1

Image-Text-to-Text
Transformers
PyTorch
vision-encoder-decoder
Model card Files
xet
 Community
1
dasomoh commited on
Commit
ff957e5
·
1 Parent(s): c43cc9c

Training started

Browse files
Files changed (6) hide show
  1. added_tokens.json +68 -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 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_affiliation>": 57586,
3
+ "</s_en_affiliation(0)>": 57546,
4
+ "</s_en_affiliation(1)>": 57548,
5
+ "</s_en_affiliation(2)>": 57556,
6
+ "</s_en_affiliation(3)>": 57566,
7
+ "</s_en_affiliation(4)>": 57576,
8
+ "</s_en_author(0)>": 57536,
9
+ "</s_en_author(1)>": 57538,
10
+ "</s_en_author(2)>": 57540,
11
+ "</s_en_author(3)>": 57552,
12
+ "</s_en_author(4)>": 57560,
13
+ "</s_en_author(5)>": 57562,
14
+ "</s_en_author(6)>": 57564,
15
+ "</s_en_author(7)>": 57580,
16
+ "</s_en_author(8)>": 57584,
17
+ "</s_en_title>": 57528,
18
+ "</s_ko_affiliation(0)>": 57542,
19
+ "</s_ko_affiliation(1)>": 57544,
20
+ "</s_ko_affiliation(2)>": 57554,
21
+ "</s_ko_affiliation(3)>": 57572,
22
+ "</s_ko_affiliation(4)>": 57574,
23
+ "</s_ko_author(0)>": 57530,
24
+ "</s_ko_author(1)>": 57532,
25
+ "</s_ko_author(2)>": 57534,
26
+ "</s_ko_author(3)>": 57550,
27
+ "</s_ko_author(4)>": 57558,
28
+ "</s_ko_author(5)>": 57568,
29
+ "</s_ko_author(6)>": 57570,
30
+ "</s_ko_author(7)>": 57578,
31
+ "</s_ko_author(8)>": 57582,
32
+ "</s_ko_title>": 57526,
33
+ "<s_affiliation>": 57585,
34
+ "<s_cord-v2>": 57587,
35
+ "<s_en_affiliation(0)>": 57545,
36
+ "<s_en_affiliation(1)>": 57547,
37
+ "<s_en_affiliation(2)>": 57555,
38
+ "<s_en_affiliation(3)>": 57565,
39
+ "<s_en_affiliation(4)>": 57575,
40
+ "<s_en_author(0)>": 57535,
41
+ "<s_en_author(1)>": 57537,
42
+ "<s_en_author(2)>": 57539,
43
+ "<s_en_author(3)>": 57551,
44
+ "<s_en_author(4)>": 57559,
45
+ "<s_en_author(5)>": 57561,
46
+ "<s_en_author(6)>": 57563,
47
+ "<s_en_author(7)>": 57579,
48
+ "<s_en_author(8)>": 57583,
49
+ "<s_en_title>": 57527,
50
+ "<s_iitcdip>": 57523,
51
+ "<s_ko_affiliation(0)>": 57541,
52
+ "<s_ko_affiliation(1)>": 57543,
53
+ "<s_ko_affiliation(2)>": 57553,
54
+ "<s_ko_affiliation(3)>": 57571,
55
+ "<s_ko_affiliation(4)>": 57573,
56
+ "<s_ko_author(0)>": 57529,
57
+ "<s_ko_author(1)>": 57531,
58
+ "<s_ko_author(2)>": 57533,
59
+ "<s_ko_author(3)>": 57549,
60
+ "<s_ko_author(4)>": 57557,
61
+ "<s_ko_author(5)>": 57567,
62
+ "<s_ko_author(6)>": 57569,
63
+ "<s_ko_author(7)>": 57577,
64
+ "<s_ko_author(8)>": 57581,
65
+ "<s_ko_title>": 57525,
66
+ "<s_synthdog>": 57524,
67
+ "<sep/>": 57522
68
+ }
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
+ 1280,
24
+ 1920
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
+ }