nielsr HF staff commited on
Commit
18ced62
1 Parent(s): ffa3509

Upload processor

Browse files
.gitattributes CHANGED
@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
30
  *.zip filter=lfs diff=lfs merge=lfs -text
31
  *.zst filter=lfs diff=lfs merge=lfs -text
32
  *tfevents* filter=lfs diff=lfs merge=lfs -text
33
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_ocr": true,
3
+ "do_resize": true,
4
+ "feature_extractor_type": "LayoutLMv2FeatureExtractor",
5
+ "ocr_lang": "fra",
6
+ "processor_class": "LayoutXLMProcessor",
7
+ "resample": 2,
8
+ "size": 224,
9
+ "tesseract_config": ""
10
+ }
special_tokens_map.json CHANGED
@@ -5,7 +5,7 @@
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
3
+ size 17082925
tokenizer_config.json CHANGED
@@ -26,6 +26,7 @@
26
  0
27
  ],
28
  "pad_token_label": -100,
 
29
  "sep_token": "</s>",
30
  "sep_token_box": [
31
  1000,
@@ -33,7 +34,6 @@
33
  1000,
34
  1000
35
  ],
36
- "sp_model_kwargs": {},
37
  "special_tokens_map_file": null,
38
  "tokenizer_class": "LayoutXLMTokenizer",
39
  "unk_token": "<unk>"
 
26
  0
27
  ],
28
  "pad_token_label": -100,
29
+ "processor_class": "LayoutXLMProcessor",
30
  "sep_token": "</s>",
31
  "sep_token_box": [
32
  1000,
 
34
  1000,
35
  1000
36
  ],
 
37
  "special_tokens_map_file": null,
38
  "tokenizer_class": "LayoutXLMTokenizer",
39
  "unk_token": "<unk>"