Hugging Face's logo

Amani123
/
Donut

Image-Text-to-Text
Transformers
PyTorch
vision-encoder-decoder
Inference Endpoints
Model card Files Community
Amani123 commited on
Commit
703705c
·
1 Parent(s): e126f37

Training done

Browse files
Files changed (6) hide show
  1. added_tokens.json +96 -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 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_A>": 57526,
3
+ "</s_B>": 57528,
4
+ "</s_C1>": 57530,
5
+ "</s_C3>": 57534,
6
+ "</s_C4a>": 57532,
7
+ "</s_CERTIFMATRICULE_1>": 57590,
8
+ "</s_CERTIFMATRICULE_2>": 57592,
9
+ "</s_CERTIFMATRICULE_3>": 57594,
10
+ "</s_CERTIFMATRICULE_4>": 57596,
11
+ "</s_CERTIFMATRICULE_5>": 57598,
12
+ "</s_CERTIFMATRICULE_6>": 57600,
13
+ "</s_D1>": 57536,
14
+ "</s_D2.1>": 57608,
15
+ "</s_D2>": 57602,
16
+ "</s_D3>": 57540,
17
+ "</s_E>": 57542,
18
+ "</s_F1>": 57544,
19
+ "</s_F2>": 57546,
20
+ "</s_F3>": 57548,
21
+ "</s_G1>": 57552,
22
+ "</s_G>": 57550,
23
+ "</s_I>": 57586,
24
+ "</s_J1>": 57556,
25
+ "</s_J2>": 57610,
26
+ "</s_J3>": 57558,
27
+ "</s_J>": 57554,
28
+ "</s_K>": 57560,
29
+ "</s_P1>": 57562,
30
+ "</s_P2>": 57564,
31
+ "</s_P3>": 57566,
32
+ "</s_P6>": 57588,
33
+ "</s_S1>": 57538,
34
+ "</s_U1>": 57604,
35
+ "</s_U2>": 57568,
36
+ "</s_V7>": 57612,
37
+ "</s_V9>": 57570,
38
+ "</s_X1>": 57572,
39
+ "</s_Y1>": 57574,
40
+ "</s_Y2>": 57576,
41
+ "</s_Y3>": 57578,
42
+ "</s_Y4>": 57580,
43
+ "</s_Y5>": 57582,
44
+ "</s_Y6>": 57584,
45
+ "</s_Z1>": 57606,
46
+ "</s_Z2>": 57614,
47
+ "<s_A>": 57525,
48
+ "<s_B>": 57527,
49
+ "<s_C1>": 57529,
50
+ "<s_C3>": 57533,
51
+ "<s_C4a>": 57531,
52
+ "<s_CERTIFMATRICULE_1>": 57589,
53
+ "<s_CERTIFMATRICULE_2>": 57591,
54
+ "<s_CERTIFMATRICULE_3>": 57593,
55
+ "<s_CERTIFMATRICULE_4>": 57595,
56
+ "<s_CERTIFMATRICULE_5>": 57597,
57
+ "<s_CERTIFMATRICULE_6>": 57599,
58
+ "<s_D1>": 57535,
59
+ "<s_D2.1>": 57607,
60
+ "<s_D2>": 57601,
61
+ "<s_D3>": 57539,
62
+ "<s_E>": 57541,
63
+ "<s_F1>": 57543,
64
+ "<s_F2>": 57545,
65
+ "<s_F3>": 57547,
66
+ "<s_G1>": 57551,
67
+ "<s_G>": 57549,
68
+ "<s_I>": 57585,
69
+ "<s_J1>": 57555,
70
+ "<s_J2>": 57609,
71
+ "<s_J3>": 57557,
72
+ "<s_J>": 57553,
73
+ "<s_K>": 57559,
74
+ "<s_P1>": 57561,
75
+ "<s_P2>": 57563,
76
+ "<s_P3>": 57565,
77
+ "<s_P6>": 57587,
78
+ "<s_S1>": 57537,
79
+ "<s_U1>": 57603,
80
+ "<s_U2>": 57567,
81
+ "<s_V7>": 57611,
82
+ "<s_V9>": 57569,
83
+ "<s_X1>": 57571,
84
+ "<s_Y1>": 57573,
85
+ "<s_Y2>": 57575,
86
+ "<s_Y3>": 57577,
87
+ "<s_Y4>": 57579,
88
+ "<s_Y5>": 57581,
89
+ "<s_Y6>": 57583,
90
+ "<s_Z1>": 57605,
91
+ "<s_Z2>": 57613,
92
+ "<s_cord-v2>": 57615,
93
+ "<s_iitcdip>": 57523,
94
+ "<s_synthdog>": 57524,
95
+ "<sep/>": 57522
96
+ }
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
+ 1100,
24
+ 820
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
+ }