Rasi1610 commited on
Commit
6451cad
1 Parent(s): ef5e413

Training done

Browse files
added_tokens.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Age>": 57536,
3
+ "</s_Father>": 57550,
4
+ "</s_Mother>": 57552,
5
+ "</s_Race>": 57546,
6
+ "</s_State file #>": 57528,
7
+ "</s_birth_day>": 57538,
8
+ "</s_birth_place>": 57540,
9
+ "</s_city>": 57544,
10
+ "</s_county>": 57542,
11
+ "</s_death>": 57532,
12
+ "</s_name>": 57530,
13
+ "</s_person>": 57526,
14
+ "</s_person_data>": 57534,
15
+ "</s_relation>": 57548,
16
+ "<s_Age>": 57535,
17
+ "<s_Father>": 57549,
18
+ "<s_Mother>": 57551,
19
+ "<s_Race>": 57545,
20
+ "<s_State file #>": 57527,
21
+ "<s_birth_day>": 57537,
22
+ "<s_birth_place>": 57539,
23
+ "<s_city>": 57543,
24
+ "<s_cord-v2>": 57553,
25
+ "<s_county>": 57541,
26
+ "<s_death>": 57531,
27
+ "<s_iitcdip>": 57523,
28
+ "<s_name>": 57529,
29
+ "<s_person>": 57525,
30
+ "<s_person_data>": 57533,
31
+ "<s_relation>": 57547,
32
+ "<s_synthdog>": 57524,
33
+ "<sep/>": 57522
34
+ }
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
+ 900,
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
+ }