Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 126,
-  "<s>": 125
+  "</s>": 76,
+  "<s>": 75
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "123": {
+    "73": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "124": {
+    "74": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "125": {
+    "75": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "126": {
+    "76": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,127 +1,77 @@
 {
-  "&": 1,
-  "(": 2,
-  ")": 3,
-  "A": 4,
-  "B": 5,
-  "C": 6,
-  "D": 7,
-  "E": 8,
-  "F": 9,
-  "G": 10,
-  "H": 11,
-  "I": 12,
-  "J": 13,
-  "K": 14,
-  "L": 15,
-  "M": 16,
-  "N": 17,
-  "O": 18,
-  "P": 19,
-  "Q": 20,
-  "R": 21,
-  "S": 22,
-  "T": 23,
-  "U": 24,
-  "V": 25,
-  "W": 26,
-  "X": 27,
-  "Y": 28,
-  "Z": 29,
-  "[PAD]": 124,
-  "[UNK]": 123,
-  "_": 30,
-  "`": 31,
-  "a": 32,
-  "b": 33,
-  "c": 34,
-  "d": 35,
-  "e": 36,
-  "f": 37,
-  "g": 38,
-  "h": 39,
-  "i": 40,
-  "j": 41,
-  "k": 42,
-  "l": 43,
-  "m": 44,
-  "n": 45,
-  "o": 46,
-  "p": 47,
-  "q": 48,
-  "r": 49,
-  "s": 50,
-  "t": 51,
-  "u": 52,
-  "v": 53,
-  "w": 54,
-  "x": 55,
-  "y": 56,
-  "z": 57,
+  "C": 1,
+  "G": 2,
+  "H": 3,
+  "N": 4,
+  "S": 5,
+  "T": 6,
+  "W": 7,
+  "[PAD]": 74,
+  "[UNK]": 73,
+  "a": 8,
+  "b": 9,
+  "c": 10,
+  "e": 11,
+  "g": 12,
+  "h": 13,
+  "i": 14,
+  "l": 15,
+  "m": 16,
+  "n": 17,
+  "o": 18,
+  "r": 19,
+  "s": 20,
+  "t": 21,
+  "u": 22,
+  "v": 23,
   "|": 0,
-  "·": 58,
-  "½": 59,
-  "á": 60,
-  "é": 61,
-  "ô": 62,
-  "š": 63,
-  "ஃ": 64,
-  "அ": 65,
-  "ஆ": 66,
-  "இ": 67,
-  "ஈ": 68,
-  "உ": 69,
-  "ஊ": 70,
-  "எ": 71,
-  "ஏ": 72,
-  "ஐ": 73,
-  "ஒ": 74,
-  "ஓ": 75,
-  "ஔ": 76,
-  "க": 77,
-  "ங": 78,
-  "ச": 79,
-  "ஜ": 80,
-  "ஞ": 81,
-  "ட": 82,
-  "ண": 83,
-  "த": 84,
-  "ந": 85,
-  "ன": 86,
-  "ப": 87,
-  "ம": 88,
-  "ய": 89,
-  "ர": 90,
-  "ற": 91,
-  "ல": 92,
-  "ள": 93,
-  "ழ": 94,
-  "வ": 95,
-  "ஷ": 96,
-  "ஸ": 97,
-  "ஹ": 98,
-  "ா": 99,
-  "ி": 100,
-  "ீ": 101,
-  "ு": 102,
-  "ூ": 103,
-  "ெ": 104,
-  "ே": 105,
-  "ை": 106,
-  "ொ": 107,
-  "ோ": 108,
-  "ௌ": 109,
-  "்": 110,
-  "ௗ": 111,
-  "ഥ": 112,
-  "–": 113,
-  "—": 114,
-  "’": 115,
-  "‚": 116,
-  "•": 117,
-  "…": 118,
-  "′": 119,
-  "″": 120,
-  "●": 121,
-  "◯": 122
+  "ஃ": 24,
+  "அ": 25,
+  "ஆ": 26,
+  "இ": 27,
+  "ஈ": 28,
+  "உ": 29,
+  "ஊ": 30,
+  "எ": 31,
+  "ஏ": 32,
+  "ஐ": 33,
+  "ஒ": 34,
+  "ஓ": 35,
+  "க": 36,
+  "ங": 37,
+  "ச": 38,
+  "ஜ": 39,
+  "ஞ": 40,
+  "ட": 41,
+  "ண": 42,
+  "த": 43,
+  "ந": 44,
+  "ன": 45,
+  "ப": 46,
+  "ம": 47,
+  "ய": 48,
+  "ர": 49,
+  "ற": 50,
+  "ல": 51,
+  "ள": 52,
+  "ழ": 53,
+  "வ": 54,
+  "ஷ": 55,
+  "ஸ": 56,
+  "ஹ": 57,
+  "ா": 58,
+  "ி": 59,
+  "ீ": 60,
+  "ு": 61,
+  "ூ": 62,
+  "ெ": 63,
+  "ே": 64,
+  "ை": 65,
+  "ொ": 66,
+  "ோ": 67,
+  "ௌ": 68,
+  "்": 69,
+  "—": 70,
+  "’": 71,
+  "●": 72
 }