Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 39,
-  "<s>": 38
+  "</s>": 40,
+  "<s>": 39
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "36": {
+    "37": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "37": {
+    "38": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "38": {
+    "39": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "39": {
+    "40": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,40 +1,41 @@
 {
-  "[PAD]": 37,
-  "[UNK]": 36,
-  "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,
+  "'": 1,
+  "[PAD]": 38,
+  "[UNK]": 37,
+  "a": 2,
+  "b": 3,
+  "c": 4,
+  "d": 5,
+  "e": 6,
+  "f": 7,
+  "g": 8,
+  "h": 9,
+  "i": 10,
+  "j": 11,
+  "k": 12,
+  "l": 13,
+  "m": 14,
+  "n": 15,
+  "o": 16,
+  "p": 17,
+  "q": 18,
+  "r": 19,
+  "s": 20,
+  "t": 21,
+  "u": 22,
+  "v": 23,
+  "w": 24,
+  "x": 25,
+  "y": 26,
+  "z": 27,
   "|": 0,
-  "à": 27,
-  "ô": 28,
-  "ú": 29,
-  "đ": 30,
-  "ạ": 31,
-  "ả": 32,
-  "ậ": 33,
-  "ắ": 34,
-  "ồ": 35
+  "à": 28,
+  "ô": 29,
+  "ú": 30,
+  "đ": 31,
+  "ạ": 32,
+  "ả": 33,
+  "ậ": 34,
+  "ắ": 35,
+  "ồ": 36
 }