Upload tokenizer

added_tokens.json

@@ -1,7 +1,6 @@
 {
-  "</s>": 105,
-  "<pad>": 107,
-  "<s>": 104,
-  "<unk>": 106,
-  "[PAD]": 103
+  "</s>": 78,
+  "<pad>": 80,
+  "<s>": 77,
+  "<unk>": 79
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "102": {
+    "75": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "103": {
+    "76": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "104": {
+    "77": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "105": {
+    "78": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "106": {
+    "79": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,7 @@
       "single_word": false,
       "special": true
     },
-    "107": {
+    "80": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,106 +1,79 @@
 {
-  "[PAD]": 103,
-  "[UNK]": 102,
+  "[PAD]": 76,
+  "[UNK]": 75,
   "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,
+  "h": 2,
+  "t": 3,
   "|": 0,
-  " ": 28,
-  "ँ": 29,
-  "ं": 30,
-  "ः": 31,
-  "अ": 32,
-  "आ": 33,
-  "इ": 34,
-  "ई": 35,
-  "उ": 36,
-  "ऊ": 37,
-  "ऋ": 38,
-  "ऍ": 39,
-  "ए": 40,
-  "ऐ": 41,
-  "ऑ": 42,
-  "ओ": 43,
-  "औ": 44,
-  "क": 45,
-  "ख": 46,
-  "ग": 47,
-  "घ": 48,
-  "च": 49,
-  "छ": 50,
-  "ज": 51,
-  "झ": 52,
-  "ञ": 53,
-  "ट": 54,
-  "ठ": 55,
-  "ड": 56,
-  "ढ": 57,
-  "ण": 58,
-  "त": 59,
-  "थ": 60,
-  "द": 61,
-  "ध": 62,
-  "न": 63,
-  "प": 64,
-  "फ": 65,
-  "ब": 66,
-  "भ": 67,
-  "म": 68,
-  "य": 69,
-  "र": 70,
-  "ऱ": 71,
-  "ल": 72,
-  "ळ": 73,
-  "व": 74,
-  "श": 75,
-  "ष": 76,
-  "स": 77,
-  "ह": 78,
-  "़": 79,
-  "ा": 80,
-  "ि": 81,
-  "ी": 82,
-  "ु": 83,
-  "ू": 84,
-  "ृ": 85,
-  "ॅ": 86,
-  "े": 87,
-  "ै": 88,
-  "ॉ": 89,
-  "ो": 90,
-  "ौ": 91,
-  "्": 92,
-  "क़": 93,
-  "ख़": 94,
-  "ज़": 95,
-  "ड़": 96,
-  "ढ़": 97,
-  "फ़": 98,
-  "।": 99,
-  "२": 100,
-  "‌": 101,
-  "’": 102
+  " ": 4,
+  "ँ": 5,
+  "ं": 6,
+  "ः": 7,
+  "अ": 8,
+  "आ": 9,
+  "इ": 10,
+  "ई": 11,
+  "उ": 12,
+  "ऊ": 13,
+  "ऋ": 14,
+  "ऍ": 15,
+  "ए": 16,
+  "ऐ": 17,
+  "ऑ": 18,
+  "ओ": 19,
+  "औ": 20,
+  "क": 21,
+  "ख": 22,
+  "ग": 23,
+  "घ": 24,
+  "च": 25,
+  "छ": 26,
+  "ज": 27,
+  "झ": 28,
+  "ञ": 29,
+  "ट": 30,
+  "ठ": 31,
+  "ड": 32,
+  "ढ": 33,
+  "ण": 34,
+  "त": 35,
+  "थ": 36,
+  "द": 37,
+  "ध": 38,
+  "न": 39,
+  "प": 40,
+  "फ": 41,
+  "ब": 42,
+  "भ": 43,
+  "म": 44,
+  "य": 45,
+  "र": 46,
+  "ऱ": 47,
+  "ल": 48,
+  "ळ": 49,
+  "व": 50,
+  "श": 51,
+  "ष": 52,
+  "स": 53,
+  "ह": 54,
+  "़": 55,
+  "ा": 56,
+  "ि": 57,
+  "ी": 58,
+  "ु": 59,
+  "ू": 60,
+  "ृ": 61,
+  "े": 62,
+  "ै": 63,
+  "ॉ": 64,
+  "ो": 65,
+  "ौ": 66,
+  "्": 67,
+  "ख़": 68,
+  "ज़": 69,
+  "ड़": 70,
+  "ढ़": 71,
+  "फ़": 72,
+  "२": 73,
+  "‌": 74
 }