Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 98,
-  "<s>": 97
+  "</s>": 92,
+  "<s>": 91
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "95": {
+    "89": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "96": {
+    "90": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "97": {
+    "91": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "98": {
+    "92": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json

@@ -1,99 +1,93 @@
 {
-  "'": 45,
-  "[PAD]": 96,
-  "[UNK]": 95,
-  "a": 51,
-  "b": 3,
-  "c": 18,
-  "d": 25,
-  "e": 54,
-  "f": 11,
-  "g": 94,
-  "h": 5,
-  "i": 74,
-  "j": 37,
-  "k": 7,
-  "l": 31,
-  "m": 16,
-  "n": 21,
-  "o": 89,
-  "p": 63,
-  "q": 34,
-  "r": 70,
-  "s": 38,
-  "t": 82,
+  "[PAD]": 90,
+  "[UNK]": 89,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "g": 6,
+  "h": 7,
+  "i": 8,
+  "k": 9,
+  "l": 10,
+  "m": 11,
+  "n": 12,
+  "o": 13,
+  "p": 14,
+  "q": 15,
+  "r": 16,
+  "s": 17,
+  "t": 18,
   "u": 19,
-  "v": 40,
-  "w": 39,
-  "x": 88,
-  "y": 57,
-  "z": 26,
-  "|": 29,
-  "à": 66,
-  "á": 44,
-  "â": 83,
-  "ã": 61,
-  "è": 77,
-  "é": 93,
-  "ê": 30,
-  "ì": 56,
-  "í": 73,
-  "ò": 8,
-  "ó": 46,
-  "ô": 71,
-  "õ": 6,
-  "ù": 67,
-  "ú": 80,
-  "ý": 50,
-  "ă": 9,
-  "đ": 91,
-  "ĩ": 49,
-  "ũ": 76,
-  "ơ": 84,
-  "ư": 24,
-  "ạ": 27,
-  "ả": 22,
-  "ấ": 36,
-  "ầ": 12,
-  "ẩ": 59,
-  "ẫ": 2,
-  "ậ": 79,
-  "ắ": 42,
-  "ằ": 28,
-  "ẳ": 55,
-  "ẵ": 33,
-  "ặ": 52,
-  "ẹ": 35,
-  "ẻ": 13,
-  "ẽ": 41,
-  "ế": 65,
-  "ề": 4,
-  "ể": 15,
-  "ễ": 86,
-  "ệ": 58,
-  "ỉ": 90,
-  "ị": 64,
-  "ọ": 10,
+  "v": 20,
+  "x": 21,
+  "y": 22,
+  "|": 0,
+  "à": 23,
+  "á": 24,
+  "â": 25,
+  "ã": 26,
+  "è": 27,
+  "é": 28,
+  "ê": 29,
+  "ì": 30,
+  "í": 31,
+  "ò": 32,
+  "ó": 33,
+  "ô": 34,
+  "õ": 35,
+  "ù": 36,
+  "ú": 37,
+  "ý": 38,
+  "ă": 39,
+  "đ": 40,
+  "ĩ": 41,
+  "ũ": 42,
+  "ơ": 43,
+  "ư": 44,
+  "ạ": 45,
+  "ả": 46,
+  "ấ": 47,
+  "ầ": 48,
+  "ẩ": 49,
+  "ẫ": 50,
+  "ậ": 51,
+  "ắ": 52,
+  "ằ": 53,
+  "ẳ": 54,
+  "ẵ": 55,
+  "ặ": 56,
+  "ẹ": 57,
+  "ẻ": 58,
+  "ẽ": 59,
+  "ế": 60,
+  "ề": 61,
+  "ể": 62,
+  "ễ": 63,
+  "ệ": 64,
+  "ỉ": 65,
+  "ị": 66,
+  "ọ": 67,
   "ỏ": 68,
-  "ố": 23,
-  "ồ": 47,
-  "ổ": 81,
-  "ỗ": 1,
-  "ộ": 14,
-  "ớ": 60,
-  "ờ": 17,
-  "ở": 20,
-  "ỡ": 75,
-  "ợ": 43,
-  "ụ": 69,
-  "ủ": 78,
-  "ứ": 62,
-  "ừ": 0,
-  "ử": 72,
-  "ữ": 87,
-  "ự": 53,
-  "ỳ": 32,
-  "ỵ": 92,
-  "ỷ": 85,
-  "ỹ": 48
+  "ố": 69,
+  "ồ": 70,
+  "ổ": 71,
+  "ỗ": 72,
+  "ộ": 73,
+  "ớ": 74,
+  "ờ": 75,
+  "ở": 76,
+  "ỡ": 77,
+  "ợ": 78,
+  "ụ": 79,
+  "ủ": 80,
+  "ứ": 81,
+  "ừ": 82,
+  "ử": 83,
+  "ữ": 84,
+  "ự": 85,
+  "ỳ": 86,
+  "ỷ": 87,
+  "ỹ": 88
 }