BDomantas commited on
Commit
e8a18ce
1 Parent(s): 3b6f2aa

Upload processor

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: cc-by-nc-sa-4.0
3
- base_model: microsoft/layoutxlm-base
4
  tags:
5
  - generated_from_trainer
 
6
  datasets:
7
  - xfun
8
  model-index:
 
1
  ---
2
  license: cc-by-nc-sa-4.0
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: microsoft/layoutxlm-base
6
  datasets:
7
  - xfun
8
  model-index:
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_processor_keys": [
3
+ "images",
4
+ "do_resize",
5
+ "size",
6
+ "resample",
7
+ "apply_ocr",
8
+ "ocr_lang",
9
+ "tesseract_config",
10
+ "return_tensors",
11
+ "data_format",
12
+ "input_data_format"
13
+ ],
14
+ "apply_ocr": true,
15
+ "do_resize": true,
16
+ "image_processor_type": "LayoutLMv2FeatureExtractor",
17
+ "ocr_lang": "fra",
18
+ "processor_class": "LayoutXLMProcessor",
19
+ "resample": 2,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ },
24
+ "tesseract_config": ""
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f76fe13d42f80dcee0cb86a1aeb5f14f8909bb8a8782f7a4a4ad76697ef164
3
+ size 17083021
tokenizer_config.json CHANGED
@@ -62,6 +62,7 @@
62
  0
63
  ],
64
  "pad_token_label": -100,
 
65
  "sep_token": "</s>",
66
  "sep_token_box": [
67
  1000,
@@ -69,7 +70,6 @@
69
  1000,
70
  1000
71
  ],
72
- "sp_model_kwargs": {},
73
  "tokenizer_class": "LayoutXLMTokenizer",
74
  "unk_token": "<unk>"
75
  }
 
62
  0
63
  ],
64
  "pad_token_label": -100,
65
+ "processor_class": "LayoutXLMProcessor",
66
  "sep_token": "</s>",
67
  "sep_token_box": [
68
  1000,
 
70
  1000,
71
  1000
72
  ],
 
73
  "tokenizer_class": "LayoutXLMTokenizer",
74
  "unk_token": "<unk>"
75
  }