Hugging Face's logo

vishnu027
/
cm1132_form3_mixed-m2

Transformers
PyTorch
vision-encoder-decoder
Inference Endpoints
Model card Files Community
vishnu027 commited on
Commit
a8d337a
•
1 Parent(s): 9dacaef

Training done

Browse files
Files changed (6) hide show
  1. added_tokens.json +40 -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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Age>": 57546,
3
+ "</s_City>": 57530,
4
+ "</s_Date_of_birth>": 57544,
5
+ "</s_Date_of_death>": 57542,
6
+ "</s_FatherFullName>": 57552,
7
+ "</s_Father_Birthplacee>": 57554,
8
+ "</s_FullName>": 57532,
9
+ "</s_Gender>": 57536,
10
+ "</s_HEADER>": 57526,
11
+ "</s_Marital_Status>": 57540,
12
+ "</s_MotherFullName>": 57556,
13
+ "</s_Mother_Birthplacee>": 57558,
14
+ "</s_PERSON>": 57534,
15
+ "</s_Place_of_birth>": 57548,
16
+ "</s_Race>": 57538,
17
+ "</s_State_file_#>": 57528,
18
+ "</s_parent>": 57550,
19
+ "<s_Age>": 57545,
20
+ "<s_City>": 57529,
21
+ "<s_Date_of_birth>": 57543,
22
+ "<s_Date_of_death>": 57541,
23
+ "<s_FatherFullName>": 57551,
24
+ "<s_Father_Birthplacee>": 57553,
25
+ "<s_FullName>": 57531,
26
+ "<s_Gender>": 57535,
27
+ "<s_HEADER>": 57525,
28
+ "<s_Marital_Status>": 57539,
29
+ "<s_MotherFullName>": 57555,
30
+ "<s_Mother_Birthplacee>": 57557,
31
+ "<s_PERSON>": 57533,
32
+ "<s_Place_of_birth>": 57547,
33
+ "<s_Race>": 57537,
34
+ "<s_State_file_#>": 57527,
35
+ "<s_cord-v2>": 57559,
36
+ "<s_iitcdip>": 57523,
37
+ "<s_parent>": 57549,
38
+ "<s_synthdog>": 57524,
39
+ "<sep/>": 57522
40
+ }
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
+ 1000,
24
+ 1000
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
+ }