Upload processor

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,13 @@
+{
+  "apply_ocr": true,
+  "do_resize": true,
+  "image_processor_type": "LayoutLMv2FeatureExtractor",
+  "ocr_lang": "chi_sim",
+  "processor_class": "LayoutXLMProcessor",
+  "resample": 2,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4147c7d8584d679fcabb10e7c63ac96de865feb8a5e2b6bc9308acf93cacdb
+size 17082953

tokenizer_config.json

@@ -6,7 +6,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "1": {
       "content": "<pad>",
@@ -14,7 +14,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "2": {
       "content": "</s>",
@@ -22,7 +22,7 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "3": {
       "content": "<unk>",
@@ -30,15 +30,15 @@
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
     "250001": {
       "content": "<mask>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
   "additional_special_tokens": [],
@@ -63,6 +63,7 @@
     0
   ],
   "pad_token_label": -100,
+  "processor_class": "LayoutXLMProcessor",
   "sep_token": "</s>",
   "sep_token_box": [
     1000,
@@ -70,8 +71,6 @@
     1000,
     1000
   ],
-  "sp_model_kwargs": {},
   "tokenizer_class": "LayoutXLMTokenizer",
-  "tokenizer_file": "/root/.cache/huggingface/hub/models--microsoft--layoutxlm-base/snapshots/8e04ebc4d3ba0013cf943b697c0aedf19b06472a/tokenizer.json",
   "unk_token": "<unk>"
 }