zinc250k-tokenizer / vocab.json
yairschiff's picture
Upload tokenizer
7a07b01 verified
raw
history blame contribute delete
No virus
880 Bytes
{
"#": 5,
"(": 6,
")": 7,
"-": 8,
"/": 9,
"1": 10,
"2": 11,
"3": 12,
"4": 13,
"5": 14,
"6": 15,
"7": 16,
"8": 17,
"<bos>": 0,
"<eos>": 1,
"<mask>": 2,
"<pad>": 3,
"<unk>": 4,
"=": 18,
"Br": 19,
"C": 20,
"Cl": 21,
"F": 22,
"I": 23,
"N": 24,
"O": 25,
"P": 26,
"S": 27,
"[C@@H]": 28,
"[C@@]": 29,
"[C@H]": 30,
"[C@]": 31,
"[CH-]": 32,
"[CH2-]": 33,
"[N+]": 34,
"[N-]": 35,
"[NH+]": 36,
"[NH-]": 37,
"[NH2+]": 38,
"[NH3+]": 39,
"[O+]": 40,
"[O-]": 41,
"[OH+]": 42,
"[P+]": 43,
"[P@@H]": 44,
"[P@@]": 45,
"[P@]": 46,
"[PH+]": 47,
"[PH2]": 48,
"[PH]": 49,
"[S+]": 50,
"[S-]": 51,
"[S@@+]": 52,
"[S@@]": 53,
"[S@]": 54,
"[SH+]": 55,
"[n+]": 56,
"[n-]": 57,
"[nH+]": 58,
"[nH]": 59,
"[o+]": 60,
"[s+]": 61,
"\\": 62,
"c": 63,
"n": 64,
"o": 65,
"s": 66
}