stevethecur
commited on
Commit
•
5e1d919
1
Parent(s):
7afc058
Upload processor
Browse files- preprocessor_config.json +14 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +38 -0
- vocab.txt +0 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
|
5 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
6 |
+
"ocr_lang": null,
|
7 |
+
"processor_class": "LayoutLMv2Processor",
|
8 |
+
"resample": 2,
|
9 |
+
"size": {
|
10 |
+
"height": 224,
|
11 |
+
"width": 224
|
12 |
+
},
|
13 |
+
"tesseract_config": ""
|
14 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"apply_ocr": false,
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"cls_token_box": [
|
7 |
+
0,
|
8 |
+
0,
|
9 |
+
0,
|
10 |
+
0
|
11 |
+
],
|
12 |
+
"do_basic_tokenize": true,
|
13 |
+
"do_lower_case": true,
|
14 |
+
"mask_token": "[MASK]",
|
15 |
+
"model_max_length": 512,
|
16 |
+
"never_split": null,
|
17 |
+
"only_label_first_subword": true,
|
18 |
+
"pad_token": "[PAD]",
|
19 |
+
"pad_token_box": [
|
20 |
+
0,
|
21 |
+
0,
|
22 |
+
0,
|
23 |
+
0
|
24 |
+
],
|
25 |
+
"pad_token_label": -100,
|
26 |
+
"processor_class": "LayoutLMv2Processor",
|
27 |
+
"sep_token": "[SEP]",
|
28 |
+
"sep_token_box": [
|
29 |
+
1000,
|
30 |
+
1000,
|
31 |
+
1000,
|
32 |
+
1000
|
33 |
+
],
|
34 |
+
"strip_accents": null,
|
35 |
+
"tokenize_chinese_chars": true,
|
36 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
37 |
+
"unk_token": "[UNK]"
|
38 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|