Improved model (processor): step 250

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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>"
 }

tokenizer_config.json

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