Improved model (processor): step 250

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,24 +1,20 @@
 {
-  "bos_token": "<s>",
-  "cls_token": "<s>",
+  "additional_special_tokens": null,
+  "cls_token": "[CLS]",
   "cls_token_box": [
     0,
     0,
     0,
     0
   ],
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "name_or_path": "microsoft/layoutxlm-base",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "microsoft/layoutlmv2-base-uncased",
+  "never_split": null,
   "only_label_first_subword": true,
-  "pad_token": "<pad>",
+  "pad_token": "[PAD]",
   "pad_token_box": [
     0,
     0,
@@ -26,15 +22,17 @@
     0
   ],
   "pad_token_label": -100,
-  "sep_token": "</s>",
+  "processor_class": "LayoutLMv2Processor",
+  "sep_token": "[SEP]",
   "sep_token_box": [
     1000,
     1000,
     1000,
     1000
   ],
-  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "tokenizer_class": "LayoutXLMTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMv2Tokenizer",
+  "unk_token": "[UNK]"
 }