added_tokens.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_Chart_title>": 57538,
3
+ "</s_X_label>": 57536,
4
+ "</s_Y_label>": 57534,
5
+ "</s_x_ticks>": 57532,
6
+ "</s_x_title>": 57530,
7
+ "</s_y_ticks>": 57528,
8
+ "</s_y_title>": 57526,
9
+ "<s_Chart_title>": 57537,
10
+ "<s_X_label>": 57535,
11
+ "<s_Y_label>": 57533,
12
+ "<s_iitcdip>": 57523,
13
+ "<s_synthdog>": 57524,
14
+ "<s_x_ticks>": 57531,
15
+ "<s_x_title>": 57529,
16
+ "<s_y_ticks>": 57527,
17
+ "<s_y_title>": 57525,
18
+ "<sep/>": 57522,
19
+ "<xt>": 57539
20
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": true,
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
+ "height": 512,
24
+ "width": 512
25
+ }
26
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s_y_title>",
4
+ "</s_y_title>",
5
+ "<s_y_ticks>",
6
+ "</s_y_ticks>",
7
+ "<s_x_title>",
8
+ "</s_x_title>",
9
+ "<s_x_ticks>",
10
+ "</s_x_ticks>",
11
+ "<s_Y_label>",
12
+ "</s_Y_label>",
13
+ "<s_X_label>",
14
+ "</s_X_label>",
15
+ "<s_Chart_title>",
16
+ "</s_Chart_title>",
17
+ "<s>",
18
+ "</s>",
19
+ "<xt>"
20
+ ],
21
+ "bos_token": "<s>",
22
+ "cls_token": "<s>",
23
+ "eos_token": "</s>",
24
+ "mask_token": {
25
+ "content": "<mask>",
26
+ "lstrip": true,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": "<pad>",
32
+ "sep_token": "</s>",
33
+ "unk_token": "<unk>"
34
+ }
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
+ }