feat: donut processor file
Browse files- .gitignore +1 -0
- added_tokens.json +49 -0
- preprocessor_config.json +26 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +63 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
.idea
|
added_tokens.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_Abstract>": 57566,
|
3 |
+
"</s_Address>": 57552,
|
4 |
+
"</s_Advertisement>": 57564,
|
5 |
+
"</s_Author>": 57550,
|
6 |
+
"</s_Caption>": 57536,
|
7 |
+
"</s_Chart>": 57562,
|
8 |
+
"</s_Field-Name>": 57556,
|
9 |
+
"</s_Footer>": 57534,
|
10 |
+
"</s_Formula>": 57568,
|
11 |
+
"</s_Header>": 57542,
|
12 |
+
"</s_Headline>": 57546,
|
13 |
+
"</s_Link>": 57540,
|
14 |
+
"</s_List-item>": 57532,
|
15 |
+
"</s_Metadata>": 57558,
|
16 |
+
"</s_Misc>": 57530,
|
17 |
+
"</s_Page number>": 57548,
|
18 |
+
"</s_Subheadline>": 57528,
|
19 |
+
"</s_Table>": 57538,
|
20 |
+
"</s_Text>": 57526,
|
21 |
+
"</s_Threading>": 57554,
|
22 |
+
"</s_Title>": 57560,
|
23 |
+
"</s_Value>": 57544,
|
24 |
+
"<s_Abstract>": 57565,
|
25 |
+
"<s_Address>": 57551,
|
26 |
+
"<s_Advertisement>": 57563,
|
27 |
+
"<s_Author>": 57549,
|
28 |
+
"<s_Caption>": 57535,
|
29 |
+
"<s_Chart>": 57561,
|
30 |
+
"<s_Field-Name>": 57555,
|
31 |
+
"<s_Footer>": 57533,
|
32 |
+
"<s_Formula>": 57567,
|
33 |
+
"<s_Header>": 57541,
|
34 |
+
"<s_Headline>": 57545,
|
35 |
+
"<s_Link>": 57539,
|
36 |
+
"<s_List-item>": 57531,
|
37 |
+
"<s_Metadata>": 57557,
|
38 |
+
"<s_Misc>": 57529,
|
39 |
+
"<s_Page number>": 57547,
|
40 |
+
"<s_Subheadline>": 57527,
|
41 |
+
"<s_Table>": 57537,
|
42 |
+
"<s_Text>": 57525,
|
43 |
+
"<s_Threading>": 57553,
|
44 |
+
"<s_Title>": 57559,
|
45 |
+
"<s_Value>": 57543,
|
46 |
+
"<s_iitcdip>": 57523,
|
47 |
+
"<s_synthdog>": 57524,
|
48 |
+
"<sep/>": 57522
|
49 |
+
}
|
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 |
+
720,
|
24 |
+
960
|
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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_Text>",
|
4 |
+
"</s_Text>",
|
5 |
+
"<s_Subheadline>",
|
6 |
+
"</s_Subheadline>",
|
7 |
+
"<s_Misc>",
|
8 |
+
"</s_Misc>",
|
9 |
+
"<s_List-item>",
|
10 |
+
"</s_List-item>",
|
11 |
+
"<s_Footer>",
|
12 |
+
"</s_Footer>",
|
13 |
+
"<s_Caption>",
|
14 |
+
"</s_Caption>",
|
15 |
+
"<s_Table>",
|
16 |
+
"</s_Table>",
|
17 |
+
"<s_Link>",
|
18 |
+
"</s_Link>",
|
19 |
+
"<s_Header>",
|
20 |
+
"</s_Header>",
|
21 |
+
"<s_Value>",
|
22 |
+
"</s_Value>",
|
23 |
+
"<s_Headline>",
|
24 |
+
"</s_Headline>",
|
25 |
+
"<s_Page number>",
|
26 |
+
"</s_Page number>",
|
27 |
+
"<s_Author>",
|
28 |
+
"</s_Author>",
|
29 |
+
"<s_Address>",
|
30 |
+
"</s_Address>",
|
31 |
+
"<s_Threading>",
|
32 |
+
"</s_Threading>",
|
33 |
+
"<s_Field-Name>",
|
34 |
+
"</s_Field-Name>",
|
35 |
+
"<s_Metadata>",
|
36 |
+
"</s_Metadata>",
|
37 |
+
"<s_Title>",
|
38 |
+
"</s_Title>",
|
39 |
+
"<s_Chart>",
|
40 |
+
"</s_Chart>",
|
41 |
+
"<s_Advertisement>",
|
42 |
+
"</s_Advertisement>",
|
43 |
+
"<s_Abstract>",
|
44 |
+
"</s_Abstract>",
|
45 |
+
"<s_Formula>",
|
46 |
+
"</s_Formula>",
|
47 |
+
"<s>",
|
48 |
+
"</s>"
|
49 |
+
],
|
50 |
+
"bos_token": "<s>",
|
51 |
+
"cls_token": "<s>",
|
52 |
+
"eos_token": "</s>",
|
53 |
+
"mask_token": {
|
54 |
+
"content": "<mask>",
|
55 |
+
"lstrip": true,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false
|
59 |
+
},
|
60 |
+
"pad_token": "<pad>",
|
61 |
+
"sep_token": "</s>",
|
62 |
+
"unk_token": "<unk>"
|
63 |
+
}
|
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 |
+
}
|