Upload tokenizer

added_tokens.json

@@ -1,5 +1,5 @@
 {
-  "</s>": 137,
-  "<s>": 136,
-  "[PAD]": 135
+  "</s>": 113,
+  "<s>": 112,
+  "[PAD]": 111
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "134": {
+    "110": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "135": {
+    "111": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "136": {
+    "112": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "137": {
+    "113": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -8,131 +8,107 @@
   ".": 7,
   ":": 8,
   "?": 9,
-  "A": 10,
-  "B": 11,
-  "C": 12,
-  "D": 13,
-  "E": 14,
-  "F": 15,
-  "G": 16,
-  "H": 17,
-  "I": 18,
-  "J": 19,
-  "K": 20,
-  "L": 21,
-  "M": 22,
-  "N": 23,
-  "O": 24,
-  "P": 25,
-  "R": 26,
-  "S": 27,
-  "T": 28,
-  "V": 29,
-  "W": 30,
-  "X": 31,
-  "Y": 32,
-  "Z": 33,
-  "[PAD]": 135,
-  "[UNK]": 134,
-  "a": 34,
-  "b": 35,
-  "c": 36,
-  "d": 37,
-  "e": 38,
-  "f": 39,
-  "g": 40,
-  "h": 41,
-  "i": 42,
-  "j": 43,
-  "k": 44,
-  "l": 45,
-  "m": 46,
-  "n": 47,
-  "o": 48,
-  "p": 49,
-  "q": 50,
-  "r": 51,
-  "s": 52,
-  "t": 53,
-  "u": 54,
-  "v": 55,
-  "w": 56,
-  "x": 57,
-  "y": 58,
-  "z": 59,
+  "[PAD]": 111,
+  "[UNK]": 110,
+  "a": 10,
+  "b": 11,
+  "c": 12,
+  "d": 13,
+  "e": 14,
+  "f": 15,
+  "g": 16,
+  "h": 17,
+  "i": 18,
+  "j": 19,
+  "k": 20,
+  "l": 21,
+  "m": 22,
+  "n": 23,
+  "o": 24,
+  "p": 25,
+  "q": 26,
+  "r": 27,
+  "s": 28,
+  "t": 29,
+  "u": 30,
+  "v": 31,
+  "w": 32,
+  "x": 33,
+  "y": 34,
+  "z": 35,
   "|": 0,
-  "ँ": 61,
-  "ं": 62,
-  "ः": 63,
-  "अ": 64,
-  "आ": 65,
-  "इ": 66,
-  "ई": 67,
-  "उ": 68,
-  "ऊ": 69,
-  "ऋ": 70,
-  "ए": 71,
-  "ऐ": 72,
-  "ऑ": 73,
-  "ओ": 74,
-  "औ": 75,
-  "क": 76,
-  "ख": 77,
-  "ग": 78,
-  "घ": 79,
-  "च": 80,
-  "छ": 81,
-  "ज": 82,
-  "झ": 83,
-  "ञ": 84,
-  "ट": 85,
-  "ठ": 86,
-  "ड": 87,
-  "ढ": 88,
-  "ण": 89,
-  "त": 90,
-  "थ": 91,
-  "द": 92,
-  "ध": 93,
-  "न": 94,
-  "प": 95,
-  "फ": 96,
-  "ब": 97,
-  "भ": 98,
-  "म": 99,
-  "य": 100,
-  "र": 101,
-  "ल": 102,
-  "व": 103,
-  "श": 104,
-  "ष": 105,
-  "स": 106,
-  "ह": 107,
-  "़": 108,
-  "ा": 109,
-  "ि": 110,
-  "ी": 111,
-  "ु": 112,
-  "ू": 113,
-  "ृ": 114,
-  "ॅ": 115,
-  "े": 116,
-  "ै": 117,
-  "ॉ": 118,
-  "ो": 119,
-  "ौ": 120,
-  "्": 121,
-  "क़": 122,
-  "ख़": 123,
-  "ग़": 124,
-  "ज़": 125,
-  "ड़": 126,
-  "ढ़": 127,
-  "फ़": 128,
-  "।": 129,
-  "–": 130,
-  "‘": 131,
-  "’": 132,
-  "“": 133,
-  "”": 134
+  "ँ": 37,
+  "ं": 38,
+  "ः": 39,
+  "अ": 40,
+  "आ": 41,
+  "इ": 42,
+  "ई": 43,
+  "उ": 44,
+  "ऊ": 45,
+  "ऋ": 46,
+  "ए": 47,
+  "ऐ": 48,
+  "ऑ": 49,
+  "ओ": 50,
+  "औ": 51,
+  "क": 52,
+  "ख": 53,
+  "ग": 54,
+  "घ": 55,
+  "च": 56,
+  "छ": 57,
+  "ज": 58,
+  "झ": 59,
+  "ञ": 60,
+  "ट": 61,
+  "ठ": 62,
+  "ड": 63,
+  "ढ": 64,
+  "ण": 65,
+  "त": 66,
+  "थ": 67,
+  "द": 68,
+  "ध": 69,
+  "न": 70,
+  "प": 71,
+  "फ": 72,
+  "ब": 73,
+  "भ": 74,
+  "म": 75,
+  "य": 76,
+  "र": 77,
+  "ल": 78,
+  "व": 79,
+  "श": 80,
+  "ष": 81,
+  "स": 82,
+  "ह": 83,
+  "़": 84,
+  "ा": 85,
+  "ि": 86,
+  "ी": 87,
+  "ु": 88,
+  "ू": 89,
+  "ृ": 90,
+  "ॅ": 91,
+  "े": 92,
+  "ै": 93,
+  "ॉ": 94,
+  "ो": 95,
+  "ौ": 96,
+  "्": 97,
+  "क़": 98,
+  "ख़": 99,
+  "ग़": 100,
+  "ज़": 101,
+  "ड़": 102,
+  "ढ़": 103,
+  "फ़": 104,
+  "।": 105,
+  "–": 106,
+  "‘": 107,
+  "’": 108,
+  "“": 109,
+  "”": 110
 }