Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 65,
-  "<s>": 64
+  "</s>": 31,
+  "<s>": 30
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "62": {
+    "28": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "63": {
+    "29": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "64": {
+    "30": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "65": {
+    "31": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,66 +1,32 @@
 {
-  "0": 19,
-  "1": 27,
-  "2": 47,
-  "3": 36,
-  "4": 42,
-  "5": 52,
-  "6": 8,
-  "7": 37,
-  "8": 60,
-  "9": 32,
-  "A": 56,
-  "B": 25,
-  "C": 30,
-  "D": 38,
-  "E": 1,
-  "F": 44,
-  "G": 54,
-  "H": 23,
-  "I": 17,
-  "J": 16,
-  "K": 7,
-  "L": 4,
-  "M": 14,
-  "N": 29,
-  "O": 24,
-  "P": 9,
-  "Q": 51,
-  "R": 45,
-  "S": 48,
-  "T": 26,
-  "U": 21,
-  "V": 10,
-  "W": 2,
-  "X": 34,
-  "Y": 6,
-  "Z": 5,
-  "[PAD]": 63,
-  "[UNK]": 62,
-  "a": 53,
-  "b": 46,
-  "c": 49,
-  "d": 58,
-  "e": 3,
-  "f": 33,
-  "g": 12,
-  "h": 55,
-  "i": 28,
-  "j": 50,
-  "k": 0,
-  "l": 18,
-  "m": 15,
-  "n": 11,
-  "o": 57,
+  "'": 26,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 3,
+  "b": 11,
+  "c": 1,
+  "d": 21,
+  "e": 9,
+  "f": 8,
+  "g": 2,
+  "h": 25,
+  "i": 6,
+  "j": 14,
+  "k": 16,
+  "l": 10,
+  "m": 4,
+  "n": 24,
+  "o": 5,
   "p": 13,
-  "q": 20,
-  "r": 31,
-  "s": 35,
-  "t": 22,
-  "u": 39,
-  "v": 40,
-  "w": 43,
-  "x": 41,
-  "y": 59,
-  "|": 61
+  "q": 0,
+  "r": 15,
+  "s": 23,
+  "t": 7,
+  "u": 27,
+  "v": 20,
+  "w": 22,
+  "x": 18,
+  "y": 12,
+  "z": 19,
+  "|": 17
 }