Upload tokenizer

added_tokens.json

@@ -1,5 +1,4 @@
 {
-  "</s>": 258,
-  "<s>": 257,
-  "[PAD]": 256
+  "</s>": 259,
+  "<s>": 258
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "255": {
+    "256": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "256": {
+    "257": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "257": {
+    "258": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "258": {
+    "259": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,4 +1,5 @@
 {
+  " ": 0,
   "(": 1,
   ")": 2,
   "0": 3,
@@ -11,8 +12,8 @@
   "7": 10,
   "8": 11,
   "9": 12,
-  "[PAD]": 256,
-  "[UNK]": 255,
+  "[PAD]": 257,
+  "[UNK]": 256,
   "a": 13,
   "b": 14,
   "c": 15,
@@ -39,7 +40,7 @@
   "x": 36,
   "y": 37,
   "z": 38,
-  "|": 0,
+  "|": 39,
   "£": 40,
   "à": 41,
   "â": 42,