Upload tokenizer

added_tokens.json

@@ -1,6 +1,4 @@
 {
-  "</s>": 75,
-  "<s>": 74,
-  "[PAD]": 73,
-  "[UNK]": 72
+  "</s>": 74,
+  "<s>": 73
 }

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -1,39 +1,4 @@
 {
-  "added_tokens_decoder": {
-    "72": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "73": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "74": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "75": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "do_lower_case": false,

vocab.json

@@ -1,76 +1,75 @@
 {
-  "'": 50,
-  "[PAD]": 73,
-  "[UNK]": 72,
-  "a": 41,
-  "e": 26,
-  "f": 61,
-  "i": 52,
-  "l": 68,
-  "m": 67,
-  "p": 70,
-  "r": 12,
-  "u": 38,
-  "w": 43,
-  "|": 63,
-  "ँ": 9,
-  "ं": 24,
-  "ः": 40,
-  "अ": 66,
-  "आ": 69,
-  "इ": 32,
-  "ई": 39,
-  "उ": 46,
-  "ऊ": 10,
-  "ए": 54,
-  "ऐ": 19,
-  "ऑ": 55,
-  "ओ": 45,
-  "औ": 48,
-  "क": 1,
-  "ख": 71,
-  "ग": 64,
-  "घ": 4,
-  "च": 16,
-  "छ": 22,
-  "ज": 44,
-  "झ": 33,
-  "ट": 3,
-  "ठ": 20,
-  "ड": 31,
+  "[PAD]": 72,
+  "[UNK]": 71,
+  "a": 1,
+  "e": 2,
+  "f": 3,
+  "i": 4,
+  "l": 5,
+  "m": 6,
+  "p": 7,
+  "r": 8,
+  "u": 9,
+  "w": 10,
+  "|": 0,
+  "ँ": 11,
+  "ं": 12,
+  "ः": 13,
+  "अ": 14,
+  "आ": 15,
+  "इ": 16,
+  "ई": 17,
+  "उ": 18,
+  "ऊ": 19,
+  "ए": 20,
+  "ऐ": 21,
+  "ऑ": 22,
+  "ओ": 23,
+  "औ": 24,
+  "क": 25,
+  "ख": 26,
+  "ग": 27,
+  "घ": 28,
+  "च": 29,
+  "छ": 30,
+  "ज": 31,
+  "झ": 32,
+  "ट": 33,
+  "ठ": 34,
+  "ड": 35,
   "ढ": 36,
-  "ण": 59,
-  "त": 27,
-  "थ": 60,
-  "द": 35,
-  "ध": 11,
+  "ण": 37,
+  "त": 38,
+  "थ": 39,
+  "द": 40,
+  "ध": 41,
   "न": 42,
-  "प": 34,
-  "फ": 5,
-  "ब": 30,
-  "भ": 53,
-  "म": 8,
-  "य": 2,
-  "र": 37,
-  "ल": 65,
-  "व": 18,
-  "श": 15,
-  "ष": 14,
-  "स": 47,
-  "ह": 13,
-  "़": 7,
-  "ा": 6,
-  "ि": 21,
-  "ी": 23,
-  "ु": 28,
-  "ू": 49,
+  "प": 43,
+  "फ": 44,
+  "ब": 45,
+  "भ": 46,
+  "म": 47,
+  "य": 48,
+  "र": 49,
+  "ल": 50,
+  "व": 51,
+  "श": 52,
+  "ष": 53,
+  "स": 54,
+  "ह": 55,
+  "़": 56,
+  "ा": 57,
+  "ि": 58,
+  "ी": 59,
+  "ु": 60,
+  "ू": 61,
   "ृ": 62,
-  "े": 57,
-  "ै": 25,
-  "ॉ": 58,
-  "ो": 0,
-  "ौ": 17,
-  "्": 51,
-  "ड़": 56,
-  "।": 29
+  "े": 63,
+  "ै": 64,
+  "ॉ": 65,
+  "ो": 66,
+  "ौ": 67,
+  "्": 68,
+  "ड़": 69,
+  "।": 70
 }