Upload processor
Browse files- added_tokens.json +29 -0
- preprocessor_config.json +24 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +38 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
added_tokens.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_class>": 57523,
|
3 |
+
"<ADVE/>": 57545,
|
4 |
+
"<advertisement/>": 57524,
|
5 |
+
"<budget/>": 57525,
|
6 |
+
"<email/>": 57526,
|
7 |
+
"<file_folder/>": 57527,
|
8 |
+
"<form/>": 57528,
|
9 |
+
"<handwritten/>": 57529,
|
10 |
+
"<invoice/>": 57530,
|
11 |
+
"<letter/>": 57531,
|
12 |
+
"<memo/>": 57532,
|
13 |
+
"<news/>": 57546,
|
14 |
+
"<news_article/>": 57533,
|
15 |
+
"<note/>": 57547,
|
16 |
+
"<passport/>": 57544,
|
17 |
+
"<presentation/>": 57534,
|
18 |
+
"<questionnaire/>": 57535,
|
19 |
+
"<report/>": 57548,
|
20 |
+
"<resume/>": 57536,
|
21 |
+
"<s_class>": 57537,
|
22 |
+
"<s_iitcdip>": 57538,
|
23 |
+
"<s_rvlcdip>": 57539,
|
24 |
+
"<s_synthdog>": 57540,
|
25 |
+
"<scientific_publication/>": 57541,
|
26 |
+
"<scientific_report/>": 57542,
|
27 |
+
"<sep/>": 57522,
|
28 |
+
"<specification/>": 57543
|
29 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"do_thumbnail": true,
|
7 |
+
"feature_extractor_type": "DonutFeatureExtractor",
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
18 |
+
"processor_class": "DonutProcessor",
|
19 |
+
"resample": 2,
|
20 |
+
"size": [
|
21 |
+
960,
|
22 |
+
1280
|
23 |
+
]
|
24 |
+
}
|
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 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"</s_class>",
|
4 |
+
"<advertisement/>",
|
5 |
+
"<budget/>",
|
6 |
+
"<email/>",
|
7 |
+
"<file_folder/>",
|
8 |
+
"<form/>",
|
9 |
+
"<handwritten/>",
|
10 |
+
"<invoice/>",
|
11 |
+
"<letter/>",
|
12 |
+
"<memo/>",
|
13 |
+
"<news_article/>",
|
14 |
+
"<presentation/>",
|
15 |
+
"<questionnaire/>",
|
16 |
+
"<resume/>",
|
17 |
+
"<s_class>",
|
18 |
+
"<s_iitcdip>",
|
19 |
+
"<s_rvlcdip>",
|
20 |
+
"<s_synthdog>",
|
21 |
+
"<scientific_publication/>",
|
22 |
+
"<scientific_report/>",
|
23 |
+
"<specification/>"
|
24 |
+
],
|
25 |
+
"bos_token": "<s>",
|
26 |
+
"cls_token": "<s>",
|
27 |
+
"eos_token": "</s>",
|
28 |
+
"mask_token": {
|
29 |
+
"content": "<mask>",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"pad_token": "<pad>",
|
36 |
+
"sep_token": "</s>",
|
37 |
+
"unk_token": "<unk>"
|
38 |
+
}
|
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 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"name_or_path": "naver-clova-ix/donut-base-finetuned-rvlcdip",
|
14 |
+
"pad_token": "<pad>",
|
15 |
+
"processor_class": "DonutProcessor",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"sp_model_kwargs": {},
|
18 |
+
"special_tokens_map_file": null,
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|