Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 123,
-  "<s>": 122
+  "</s>": 95,
+  "<s>": 94
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "120": {
+    "92": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "121": {
+    "93": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "122": {
+    "94": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "123": {
+    "95": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
@@ -34,7 +34,7 @@
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
+  "clean_up_tokenization_spaces": true,
   "do_lower_case": false,
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,

vocab.json

@@ -1,124 +1,96 @@
 {
-  "\t": 0,
-  "(": 2,
-  ")": 3,
-  "/": 4,
-  "1": 5,
-  "4": 6,
-  "6": 7,
-  "8": 8,
-  "9": 9,
-  "<": 10,
-  ">": 11,
-  "@": 12,
-  "[": 13,
-  "[PAD]": 121,
-  "[UNK]": 120,
-  "\\": 14,
-  "]": 15,
-  "_": 16,
-  "`": 17,
-  "a": 18,
-  "b": 19,
-  "c": 20,
-  "d": 21,
-  "e": 22,
-  "f": 23,
-  "g": 24,
-  "h": 25,
-  "i": 26,
-  "k": 27,
-  "l": 28,
-  "m": 29,
-  "n": 30,
-  "o": 31,
-  "p": 32,
-  "q": 33,
-  "r": 34,
-  "s": 35,
-  "t": 36,
-  "u": 37,
-  "v": 38,
-  "w": 39,
-  "y": 40,
-  "{": 41,
-  "|": 1,
-  "}": 42,
-  " ": 43,
-  "ˌ": 44,
-  "́": 45,
-  "̤": 46,
-  "।": 47,
-  "ಂ": 48,
-  "ಃ": 49,
-  "ಅ": 50,
-  "ಆ": 51,
-  "ಇ": 52,
-  "ಈ": 53,
-  "ಉ": 54,
-  "ಊ": 55,
-  "ಋ": 56,
-  "ಎ": 57,
-  "ಏ": 58,
-  "ಐ": 59,
-  "ಒ": 60,
-  "ಓ": 61,
-  "ಔ": 62,
-  "ಕ": 63,
-  "ಖ": 64,
-  "ಗ": 65,
-  "ಘ": 66,
-  "ಙ": 67,
-  "ಚ": 68,
-  "ಛ": 69,
-  "ಜ": 70,
-  "ಝ": 71,
-  "ಞ": 72,
-  "ಟ": 73,
-  "ಠ": 74,
-  "ಡ": 75,
-  "ಢ": 76,
-  "ಣ": 77,
-  "ತ": 78,
-  "ಥ": 79,
-  "ದ": 80,
-  "ಧ": 81,
-  "ನ": 82,
-  "ಪ": 83,
-  "ಫ": 84,
-  "ಬ": 85,
-  "ಭ": 86,
-  "ಮ": 87,
-  "ಯ": 88,
-  "ರ": 89,
-  "ಲ": 90,
-  "ಳ": 91,
-  "ವ": 92,
-  "ಶ": 93,
-  "ಷ": 94,
-  "ಸ": 95,
-  "ಹ": 96,
-  "಼": 97,
-  "ಾ": 98,
-  "ಿ": 99,
-  "ೀ": 100,
-  "ು": 101,
-  "ೂ": 102,
-  "ೃ": 103,
-  "ೆ": 104,
-  "ೇ": 105,
-  "ೈ": 106,
-  "ೊ": 107,
-  "ೋ": 108,
-  "ೌ": 109,
-  "್": 110,
-  "ೕ": 111,
-  "೦": 112,
-  "೧": 113,
-  "೨": 114,
-  "೩": 115,
-  "೯": 116,
-  "‌": 117,
-  "‍": 118,
-  "❵": 119
+  "!": 1,
+  "'": 2,
+  "?": 3,
+  "O": 4,
+  "[PAD]": 93,
+  "[UNK]": 92,
+  "\\": 5,
+  "`": 6,
+  "a": 7,
+  "c": 8,
+  "e": 9,
+  "h": 10,
+  "i": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "r": 17,
+  "s": 18,
+  "t": 19,
+  "u": 20,
+  "v": 21,
+  "y": 22,
+  "|": 0,
+  "́": 23,
+  "̤": 24,
+  "।": 25,
+  "ಂ": 26,
+  "ಃ": 27,
+  "ಅ": 28,
+  "ಆ": 29,
+  "ಇ": 30,
+  "ಈ": 31,
+  "ಉ": 32,
+  "ಊ": 33,
+  "ಋ": 34,
+  "ಎ": 35,
+  "ಏ": 36,
+  "ಐ": 37,
+  "ಒ": 38,
+  "ಓ": 39,
+  "ಔ": 40,
+  "ಕ": 41,
+  "ಖ": 42,
+  "ಗ": 43,
+  "ಘ": 44,
+  "ಙ": 45,
+  "ಚ": 46,
+  "ಛ": 47,
+  "ಜ": 48,
+  "ಝ": 49,
+  "ಞ": 50,
+  "ಟ": 51,
+  "ಠ": 52,
+  "ಡ": 53,
+  "ಢ": 54,
+  "ಣ": 55,
+  "ತ": 56,
+  "ಥ": 57,
+  "ದ": 58,
+  "ಧ": 59,
+  "ನ": 60,
+  "ಪ": 61,
+  "ಫ": 62,
+  "ಬ": 63,
+  "ಭ": 64,
+  "ಮ": 65,
+  "ಯ": 66,
+  "ರ": 67,
+  "ಲ": 68,
+  "ಳ": 69,
+  "ವ": 70,
+  "ಶ": 71,
+  "ಷ": 72,
+  "ಸ": 73,
+  "ಹ": 74,
+  "಼": 75,
+  "ಾ": 76,
+  "ಿ": 77,
+  "ೀ": 78,
+  "ು": 79,
+  "ೂ": 80,
+  "ೃ": 81,
+  "ೆ": 82,
+  "ೇ": 83,
+  "ೈ": 84,
+  "ೊ": 85,
+  "ೋ": 86,
+  "ೌ": 87,
+  "್": 88,
+  "‌": 89,
+  "‍": 90,
+  "❵": 91
 }