nafiz09 commited on
Commit
794c6ca
·
verified ·
1 Parent(s): 9dc9b22

Training done

Browse files
added_tokens.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 32000,
3
+ "</s_address_bn>": 32025,
4
+ "</s_birth_place>": 32023,
5
+ "</s_blood_group>": 32021,
6
+ "</s_date_of_birth>": 32019,
7
+ "</s_fathers_name_bn>": 32017,
8
+ "</s_id_no>": 32015,
9
+ "</s_mothers_name_bn>": 32013,
10
+ "</s_mrz_code>": 32011,
11
+ "</s_name_bn>": 32009,
12
+ "</s_name_en>": 32007,
13
+ "</s_post_code>": 32005,
14
+ "<s_address_bn>": 32024,
15
+ "<s_birth_place>": 32022,
16
+ "<s_blood_group>": 32020,
17
+ "<s_cord-v2>": 32026,
18
+ "<s_date_of_birth>": 32018,
19
+ "<s_fathers_name_bn>": 32016,
20
+ "<s_id_no>": 32014,
21
+ "<s_mothers_name_bn>": 32012,
22
+ "<s_mrz_code>": 32010,
23
+ "<s_name_bn>": 32008,
24
+ "<s_name_en>": 32006,
25
+ "<s_post_code>": 32004,
26
+ "কুষ্টিয়া": 32001,
27
+ "নারায়ণগঞ্জ": 32003,
28
+ "ময়মনসিংহ": 32002
29
+ }
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
+ 640,
24
+ 320
25
+ ]
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "eos_token": "</s>",
4
+ "mask_token": "[MASK]",
5
+ "pad_token": "[PAD]",
6
+ "sep_token": "[SEP]",
7
+ "unk_token": "[UNK]"
8
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "full_tokenizer_file": null,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "csebuetnlp/banglabert_large",
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "processor_class": "DonutProcessor",
12
+ "sep_token": "[SEP]",
13
+ "special_tokens_map_file": null,
14
+ "strip_accents": null,
15
+ "tokenize_chinese_chars": false,
16
+ "tokenizer_class": "ElectraTokenizer",
17
+ "unk_token": "[UNK]"
18
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff