Upload tokenizer

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "20024": {
+    "20031": {
       "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "20124": {
+    "20131": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "20125": {
+    "20132": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "20126": {
+    "20133": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "20127": {
+    "20134": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,

vocab.txt

@@ -1,3 +1,10 @@
+[unused1000]
+[unused1001]
+[unused1002]
+[unused1003]
+[unused1004]
+[unused1005]
+[unused1006]
 [JV]
 [MI]
 [SU]