Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 96,
-  "<s>": 95
+  "</s>": 93,
+  "<s>": 92
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "93": {
+    "90": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "94": {
+    "91": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "95": {
+    "92": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "96": {
+    "93": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,97 +1,94 @@
 {
-  "[PAD]": 94,
-  "[UNK]": 93,
-  "a": 1,
-  "b": 2,
-  "c": 3,
-  "d": 4,
-  "e": 5,
-  "f": 6,
-  "g": 7,
-  "h": 8,
-  "i": 9,
-  "j": 10,
-  "k": 11,
-  "l": 12,
-  "m": 13,
-  "n": 14,
-  "o": 15,
-  "p": 16,
-  "q": 17,
-  "r": 18,
-  "s": 19,
-  "t": 20,
-  "u": 21,
-  "v": 22,
-  "w": 23,
-  "x": 24,
-  "y": 25,
-  "z": 26,
+  "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": 20,
+  "X": 21,
+  "Y": 22,
+  "[PAD]": 91,
+  "[UNK]": 90,
   "|": 0,
-  "à": 27,
-  "á": 28,
-  "â": 29,
-  "ã": 30,
-  "è": 31,
-  "é": 32,
-  "ê": 33,
-  "ì": 34,
-  "í": 35,
-  "ò": 36,
-  "ó": 37,
-  "ô": 38,
-  "õ": 39,
-  "ù": 40,
-  "ú": 41,
-  "ý": 42,
-  "ă": 43,
-  "đ": 44,
-  "ĩ": 45,
-  "ũ": 46,
-  "ơ": 47,
-  "ư": 48,
-  "ạ": 49,
-  "ả": 50,
-  "ấ": 51,
-  "ầ": 52,
-  "ẩ": 53,
-  "ẫ": 54,
-  "ậ": 55,
-  "ắ": 56,
-  "ằ": 57,
-  "ẳ": 58,
-  "ẵ": 59,
-  "ặ": 60,
-  "ẹ": 61,
-  "ẻ": 62,
-  "ẽ": 63,
-  "ế": 64,
-  "ề": 65,
-  "ể": 66,
-  "ễ": 67,
-  "ệ": 68,
-  "ỉ": 69,
-  "ị": 70,
-  "ọ": 71,
-  "ỏ": 72,
-  "ố": 73,
-  "ồ": 74,
-  "ổ": 75,
-  "ỗ": 76,
-  "ộ": 77,
-  "ớ": 78,
-  "ờ": 79,
-  "ở": 80,
-  "ỡ": 81,
-  "ợ": 82,
-  "ụ": 83,
-  "ủ": 84,
-  "ứ": 85,
-  "ừ": 86,
-  "ử": 87,
-  "ữ": 88,
-  "ự": 89,
-  "ỳ": 90,
-  "ỵ": 91,
-  "ỹ": 92
+  "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": 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,
+  "Ỵ": 87,
+  "Ỷ": 88,
+  "Ỹ": 89
 }