Upload tokenizer
7c719e7 verified | { |
| "\t": 0, |
| "0": 2, |
| "1": 3, |
| "2": 4, |
| "3": 5, |
| "4": 6, |
| "5": 7, |
| "6": 8, |
| "7": 9, |
| "8": 10, |
| "9": 11, |
| "[PAD]": 69, |
| "[UNK]": 68, |
| "c": 12, |
| "d": 13, |
| "f": 14, |
| "i": 15, |
| "o": 16, |
| "s": 17, |
| "v": 18, |
| "w": 19, |
| "|": 1, |
| "ஃ": 20, |
| "அ": 21, |
| "ஆ": 22, |
| "இ": 23, |
| "ஈ": 24, |
| "உ": 25, |
| "ஊ": 26, |
| "எ": 27, |
| "ஏ": 28, |
| "ஐ": 29, |
| "ஒ": 30, |
| "ஓ": 31, |
| "க": 32, |
| "ங": 33, |
| "ச": 34, |
| "ஜ": 35, |
| "ஞ": 36, |
| "ட": 37, |
| "ண": 38, |
| "த": 39, |
| "ந": 40, |
| "ன": 41, |
| "ப": 42, |
| "ம": 43, |
| "ய": 44, |
| "ர": 45, |
| "ற": 46, |
| "ல": 47, |
| "ள": 48, |
| "ழ": 49, |
| "வ": 50, |
| "ஷ": 51, |
| "ஸ": 52, |
| "ஹ": 53, |
| "ா": 54, |
| "ி": 55, |
| "ீ": 56, |
| "ு": 57, |
| "ூ": 58, |
| "ெ": 59, |
| "ே": 60, |
| "ை": 61, |
| "ொ": 62, |
| "ோ": 63, |
| "ௌ": 64, |
| "்": 65, |
| "": 66, |
| "…": 67 |
| } |
|
|