Upload tokenizer

special_tokens_map.json

@@ -1,27 +1,41 @@
 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "cls_token": {
-    "content": "[CLS]",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "[MASK]",
+  "eos_token": {
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
-    "content": "[PAD]",
+    "content": "<pad>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "[SEP]",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,64 +1,72 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "104": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30526": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
+  "cls_token": "<s>",
   "do_lower_case": true,
+  "eos_token": "</s>",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
+  "mask_token": "<mask>",
   "max_length": 128,
   "model_max_length": 512,
-  "never_split": null,
   "pad_to_multiple_of": null,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "pad_token_type_id": 0,
   "padding_side": "right",
-  "sep_token": "[SEP]",
+  "sep_token": "</s>",
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "MPNetTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"

vocab.txt

@@ -1,3 +1,7 @@
+<s>
+<pad>
+</s>
+<unk>
 [PAD]
 [unused0]
 [unused1]
@@ -30520,3 +30524,4 @@ necessitated
 ##：
 ##？
 ##～
+<mask>