Hugging Face's logo

abdogoom
/
invoices-donut-model-v1

Model card Files Community
47

Training done

#41
by abdogoom - opened
base: refs/heads/main
←
from: refs/pr/41
Discussion Files changed
+230798
-0
Files changed (6) hide show
  1. added_tokens.json +48 -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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Activité>": 57526,
3
+ "</s_Addresse_personnelle>": 57528,
4
+ "</s_Adresse_principal_etablissement>": 57530,
5
+ "</s_Au_nom>": 57532,
6
+ "</s_Capital_social(Devise)>": 57534,
7
+ "</s_Code_demande>": 57536,
8
+ "</s_Date_début>": 57538,
9
+ "</s_Date_fin>": 57540,
10
+ "</s_Date_imma>": 57542,
11
+ "</s_Dénomination>": 57544,
12
+ "</s_Enseigne>": 57546,
13
+ "</s_Forme_juridique>": 57548,
14
+ "</s_Min_si_capital_variable>": 57550,
15
+ "</s_Nom_commercial>": 57552,
16
+ "</s_Num_chrono>": 57554,
17
+ "</s_Num_header>": 57556,
18
+ "</s_Origine_de_la_société>": 57558,
19
+ "</s_Origine_fonds>": 57560,
20
+ "</s_Siege_social>": 57562,
21
+ "</s_Sigle>": 57564,
22
+ "</s_Timestamp>": 57566,
23
+ "<s_Activité>": 57525,
24
+ "<s_Addresse_personnelle>": 57527,
25
+ "<s_Adresse_principal_etablissement>": 57529,
26
+ "<s_Au_nom>": 57531,
27
+ "<s_Capital_social(Devise)>": 57533,
28
+ "<s_Code_demande>": 57535,
29
+ "<s_Date_début>": 57537,
30
+ "<s_Date_fin>": 57539,
31
+ "<s_Date_imma>": 57541,
32
+ "<s_Dénomination>": 57543,
33
+ "<s_Enseigne>": 57545,
34
+ "<s_Forme_juridique>": 57547,
35
+ "<s_Min_si_capital_variable>": 57549,
36
+ "<s_Nom_commercial>": 57551,
37
+ "<s_Num_chrono>": 57553,
38
+ "<s_Num_header>": 57555,
39
+ "<s_Origine_de_la_société>": 57557,
40
+ "<s_Origine_fonds>": 57559,
41
+ "<s_Siege_social>": 57561,
42
+ "<s_Sigle>": 57563,
43
+ "<s_Timestamp>": 57565,
44
+ "<s_cord-v2>": 57567,
45
+ "<s_iitcdip>": 57523,
46
+ "<s_synthdog>": 57524,
47
+ "<sep/>": 57522
48
+ }
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
+ }