Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 65,
-  "<s>": 64
+  "</s>": 113,
+  "<s>": 112
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "62": {
+    "110": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "63": {
+    "111": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "64": {
+    "112": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "65": {
+    "113": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,66 +1,114 @@
 {
-  "&": 54,
-  "'": 61,
-  "(": 41,
-  ")": 13,
-  "/": 23,
-  "[PAD]": 63,
-  "[UNK]": 62,
-  "a": 26,
-  "b": 28,
-  "c": 1,
-  "d": 59,
-  "e": 20,
-  "f": 2,
-  "g": 58,
-  "h": 39,
-  "i": 45,
-  "j": 42,
-  "k": 36,
-  "l": 25,
-  "m": 17,
-  "n": 56,
-  "o": 34,
-  "p": 29,
-  "q": 40,
-  "r": 43,
-  "s": 33,
-  "t": 31,
-  "u": 11,
-  "v": 47,
-  "w": 49,
-  "x": 53,
-  "y": 32,
-  "z": 3,
-  "|": 51,
-  "´": 0,
+  "&": 23,
+  "'": 68,
+  "(": 18,
+  ")": 104,
+  "/": 15,
+  "[PAD]": 111,
+  "[UNK]": 110,
+  "_": 52,
+  "a": 76,
+  "b": 29,
+  "c": 48,
+  "d": 8,
+  "e": 86,
+  "f": 62,
+  "g": 39,
+  "h": 100,
+  "i": 84,
+  "j": 98,
+  "k": 0,
+  "l": 20,
+  "m": 67,
+  "n": 92,
+  "o": 82,
+  "p": 106,
+  "q": 55,
+  "r": 59,
+  "s": 9,
+  "t": 99,
+  "u": 81,
+  "v": 46,
+  "w": 89,
+  "x": 108,
+  "y": 2,
+  "z": 33,
+  "|": 19,
+  "«": 56,
+  "´": 32,
+  "»": 25,
+  "ß": 6,
   "à": 60,
-  "á": 37,
-  "â": 8,
-  "ä": 38,
-  "è": 14,
-  "é": 24,
-  "ê": 12,
-  "ë": 35,
-  "í": 50,
-  "ï": 30,
-  "ó": 48,
-  "ô": 18,
-  "ö": 4,
-  "ú": 15,
-  "û": 19,
-  "ü": 55,
-  "ă": 21,
-  "ō": 5,
-  "ř": 57,
-  "š": 44,
-  "ţ": 10,
-  "ž": 9,
-  "–": 22,
-  "—": 7,
-  "‘": 52,
-  "’": 27,
-  "“": 16,
-  "”": 46,
-  "…": 6
+  "á": 70,
+  "â": 5,
+  "ã": 75,
+  "ä": 71,
+  "å": 54,
+  "æ": 26,
+  "è": 77,
+  "é": 17,
+  "ê": 11,
+  "ë": 30,
+  "í": 65,
+  "ï": 93,
+  "ð": 38,
+  "ñ": 83,
+  "ò": 88,
+  "ó": 97,
+  "ô": 53,
+  "ö": 16,
+  "ø": 51,
+  "ú": 90,
+  "û": 74,
+  "ü": 94,
+  "ý": 49,
+  "ā": 42,
+  "ă": 7,
+  "ą": 87,
+  "ć": 44,
+  "č": 40,
+  "ď": 79,
+  "đ": 14,
+  "ę": 47,
+  "ě": 73,
+  "ğ": 1,
+  "ī": 61,
+  "ı": 107,
+  "ł": 45,
+  "ň": 105,
+  "ō": 24,
+  "ő": 96,
+  "ř": 109,
+  "ś": 22,
+  "ş": 37,
+  "š": 72,
+  "ţ": 85,
+  "ź": 13,
+  "ž": 27,
+  "ơ": 102,
+  "ș": 103,
+  "ț": 3,
+  "ə": 64,
+  "ʻ": 63,
+  "ʿ": 21,
+  "о": 69,
+  "ѹ": 43,
+  "ả": 50,
+  "ắ": 36,
+  "–": 12,
+  "—": 95,
+  "‘": 10,
+  "’": 34,
+  "‚": 101,
+  "“": 35,
+  "”": 41,
+  "„": 58,
+  "…": 4,
+  "‹": 28,
+  "›": 80,
+  "乡": 31,
+  "幺": 78,
+  "無": 91,
+  "生": 57,
+  "辶": 66
 }