Upload processor

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv2FeatureExtractor",
+  "ocr_lang": "fra",
+  "processor_class": "LayoutXLMProcessor",
+  "resample": 2,
+  "size": 224,
+  "tesseract_config": ""
+}

special_tokens_map.json

@@ -5,7 +5,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:affcfb1f45c4b14a70a6589c3d153b430ed4309e5a6613a88dab64d5a923a5d6
+size 17082925

tokenizer_config.json

@@ -26,6 +26,7 @@
     0
   ],
   "pad_token_label": -100,
+  "processor_class": "LayoutXLMProcessor",
   "sep_token": "</s>",
   "sep_token_box": [
     1000,
@@ -33,7 +34,6 @@
     1000,
     1000
   ],
-  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
   "tokenizer_class": "LayoutXLMTokenizer",
   "unk_token": "<unk>"