VerySmollGPT-5M-Base / tokenizer.json
ayayayya
VerySmollGPT
e600974 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [],
"normalizer": null,
"pre_tokenizer": {
"type": "CharacterLevel"
},
"post_processor": null,
"decoder": null,
"model": {
"type": "CharacterLevel",
"vocab": {
"<PAD>": 0,
"<UNK>": 1,
"<BOS>": 2,
"<EOS>": 3,
"\t": 4,
"\n": 5,
" ": 6,
"!": 7,
"\"": 8,
"$": 9,
"&": 10,
"'": 11,
"(": 12,
")": 13,
"*": 14,
"+": 15,
",": 16,
"-": 17,
".": 18,
"/": 19,
"0": 20,
"1": 21,
"2": 22,
"3": 23,
"4": 24,
"5": 25,
"6": 26,
"7": 27,
"8": 28,
"9": 29,
":": 30,
";": 31,
"?": 32,
"A": 33,
"B": 34,
"C": 35,
"D": 36,
"E": 37,
"F": 38,
"G": 39,
"H": 40,
"I": 41,
"J": 42,
"K": 43,
"L": 44,
"M": 45,
"N": 46,
"O": 47,
"P": 48,
"Q": 49,
"R": 50,
"S": 51,
"T": 52,
"U": 53,
"V": 54,
"W": 55,
"X": 56,
"Y": 57,
"Z": 58,
"a": 59,
"b": 60,
"c": 61,
"d": 62,
"e": 63,
"f": 64,
"g": 65,
"h": 66,
"i": 67,
"j": 68,
"k": 69,
"l": 70,
"m": 71,
"n": 72,
"o": 73,
"p": 74,
"q": 75,
"r": 76,
"s": 77,
"t": 78,
"u": 79,
"v": 80,
"w": 81,
"x": 82,
"y": 83,
"z": 84,
" ": 85,
"¡": 86,
"¦": 87,
"©": 88,
"«": 89,
"±": 90,
"³": 91,
"´": 92,
"»": 93,
"Â": 94,
"Ã": 95,
"â": 96,
"œ": 97,
"˜": 98,
"“": 99,
"”": 100,
"‰": 101,
"€": 102,
"™": 103
},
"unk_token": "<UNK>"
}
}