Upload tokenizer

added_tokens.json

@@ -1,6 +1,6 @@
 {
-  "</s>": 78,
-  "<pad>": 80,
-  "<s>": 77,
-  "<unk>": 79
+  "</s>": 72,
+  "<pad>": 74,
+  "<s>": 71,
+  "<unk>": 73
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "75": {
+    "69": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "76": {
+    "70": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "77": {
+    "71": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "78": {
+    "72": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "79": {
+    "73": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": false,
@@ -40,7 +40,7 @@
       "single_word": false,
       "special": true
     },
-    "80": {
+    "74": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,79 +1,73 @@
 {
-  "[PAD]": 76,
-  "[UNK]": 75,
-  "a": 1,
-  "h": 2,
-  "t": 3,
+  "[PAD]": 70,
+  "[UNK]": 69,
   "|": 0,
-  " ": 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
+  "ँ": 1,
+  "ं": 2,
+  "अ": 3,
+  "आ": 4,
+  "इ": 5,
+  "ई": 6,
+  "उ": 7,
+  "ऊ": 8,
+  "ऋ": 9,
+  "ए": 10,
+  "ऐ": 11,
+  "ऑ": 12,
+  "ओ": 13,
+  "औ": 14,
+  "क": 15,
+  "ख": 16,
+  "ग": 17,
+  "घ": 18,
+  "च": 19,
+  "छ": 20,
+  "ज": 21,
+  "झ": 22,
+  "ञ": 23,
+  "ट": 24,
+  "ठ": 25,
+  "ड": 26,
+  "ढ": 27,
+  "ण": 28,
+  "त": 29,
+  "थ": 30,
+  "द": 31,
+  "ध": 32,
+  "न": 33,
+  "प": 34,
+  "फ": 35,
+  "ब": 36,
+  "भ": 37,
+  "म": 38,
+  "य": 39,
+  "र": 40,
+  "ऱ": 41,
+  "ल": 42,
+  "ळ": 43,
+  "व": 44,
+  "श": 45,
+  "ष": 46,
+  "स": 47,
+  "ह": 48,
+  "़": 49,
+  "ा": 50,
+  "ि": 51,
+  "ी": 52,
+  "ु": 53,
+  "ू": 54,
+  "ृ": 55,
+  "े": 56,
+  "ै": 57,
+  "ॉ": 58,
+  "ो": 59,
+  "ौ": 60,
+  "्": 61,
+  "ख़": 62,
+  "ज़": 63,
+  "ड़": 64,
+  "ढ़": 65,
+  "फ़": 66,
+  "२": 67,
+  "‌": 68
 }