chemical-reaction-t5-v3 / tokenizer.json
SCUER's picture
Upload tokenizer
b030b5e verified
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 256,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": "BatchLongest",
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 512,
"content": "<extra_id_0>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 513,
"content": "<extra_id_1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "Replace",
"pattern": {
"String": "\\s+"
},
"content": ""
},
{
"type": "NFKC"
}
]
},
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Split",
"pattern": {
"String": "(N\\(\\[c\\]1ccccc1\\)\\(c1ccccc1\\)c1ccccc1|c1ccccc1C\\(=O\\)OOC\\(=O\\)c1ccccc1|CC\\(C\\)\\(CN\\)N=N\\[C\\]\\(CN\\)C\\(C\\)C|c1cc\\(N\\(\\[O\\]\\)c2ccccc2\\)cc1|N\\#CC\\(C\\)\\(C\\)N=NC\\(C\\)\\(C\\)C\\#N|CC\\(C\\)\\(C\\)N\\(\\[O\\]\\)C\\(C\\)\\(C\\)C|OC\\(=O\\)C\\(=S\\)SCCCC\\[CH2\\]|c1cc\\(\\[C\\]\\)c2ccccc2c1|c1c\\(\\[C\\]\\)c2ccccc2cc1|C\\[N\\]1N=CN\\(C\\)C1=\\[N\\]|CC\\(C\\)\\(C\\)OOC\\(C\\)\\(C\\)C|c1ccc\\(\\[C\\]\\(CH3\\)\\)cc1|N1C\\(=O\\)CCC1\\(=O\\)Br|c1ccccc1C\\(=O\\)O\\[C\\]|\\[Se\\]CC\\(c1ccccc1\\)|COC\\(=O\\)OOC\\(=O\\)OC|c1ccc\\(C\\[CH2\\]\\)cc1|BrC\\(=O\\)OC\\(C\\)\\(C\\)C|\\[Si\\]\\(c1ccccc1\\)3|c1ccc2\\[nH\\]ccc12|c1ccc2\\[nH\\]cnc12|c1cccc2ncccc12|\\[P\\]\\(c1ccccc1\\)2|C1N\\(C\\)C\\(=O\\)CC1|\\[CH2\\]c1ccccc1|c1cc\\(\\[C\\]\\)ccc1|c1ccc2cnccc12|c1ccc2ccccc12|\\[CH2\\]Si\\(CH3\\)3|CC=CC=CC\\[CH2\\]|c1ccc\\(\\[C\\]\\)cc1|c1c\\(\\[C\\]\\)cccc1|\\[CH2\\]CC=CC=CC|BrCCCCC\\[CH2\\]|\\[CH2\\]P\\(CH3\\)2|C1C2CCCCC1C2|C1CCCC\\[CH\\]C1|\\[CH2\\]C\\(=O\\)OC|c1ccc2sccc12|ClCCCCC\\[CH2\\]|\\[CH2\\]N\\(CH3\\)2|c1cn2ccnc2c1|c1ccc2occc12|\\[O\\]OC\\(C\\)\\(C\\)C|c1ccccc1\\[N\\]|\\[SiH2\\]C\\(C\\)C|\\[CH2\\]CCC=CC|S\\(=O\\)\\(=O\\)Cl|CC=CCC\\[CH2\\]|\\[c1ccccc1\\+\\]|\\[CH2\\]C\\#CC\\#C|CC\\(=O\\)\\[CH2\\]|N=\\[N\\+\\]=\\[N\\-\\]|C\\(=O\\)\\[C\\]\\(C\\)|c1ccccc1\\[O\\]|\\[CH2\\]C\\(=O\\)C|\\[CH2\\]CCCC\\#C|\\[C\\]\\(C\\)\\(C\\)CN|C\\(=O\\)O\\[CH2\\]|C\\(C\\)\\(C\\)O\\[C\\]|C1CCC\\[CH\\]C1|C\\#CCCC\\[CH2\\]|c1ccccc1SeC|\\[CH2\\]C\\(=O\\)O|c1ccccc1\\[S\\]|\\[C\\]\\(=O\\)\\[O\\-\\]|c1cnn\\[nH\\]1|C1C2CCC1C2|C1CC\\[CH\\]C1|c1c\\[c\\]ccc1|c1cn\\[nH\\]c1|c1cc\\[nH\\]c1|\\[CH2=CH2\\+\\]|c1cc\\[se\\]c1|\\[CH\\]\\(CH3\\)2|\\[Si\\]\\(CH3\\)3|\\[c\\]1ccccc1|OSi\\(C\\)\\(C\\)C|C\\(=O\\)N\\(C\\)C|\\[CH2\\]C=C=C|c1ccccc1C|C1C2CC1C2|CSC\\(=S\\)OC|\\[B\\]\\(CH3\\)2|\\[CH2\\]OCH3|S\\(=O\\)\\(=O\\)|\\[P\\]\\(CH3\\)2|\\[CH2\\]SiH3|C\\(=O\\)\\[C\\]H|\\[PH\\]C\\(C\\)C|\\[CH2\\]SCH3|\\[C\\]\\(CH3\\)3|c1nccnc1|C=C\\[CH2\\]|\\[SiH2\\]CC|\\[CH2\\]PH2|C1CCOCC1|C1CCNCC1|C1CCSCC1|C\\(=S\\)\\[S\\]|\\[O\\]C\\(C\\)C|C1COCCO1|\\[CH2\\]C\\#C|c1cncnc1|\\[CH2\\]C=C|CN\\(\\[O\\]\\)C|\\[CH2\\]NO2|CC\\(=O\\)OC|c1ccncc1|C\\#C\\[CH2\\]|C=C=\\[CH\\]|CC\\[SiH2\\]|C1C\\[CH\\]1|\\[CH2\\]CH3|\\[CH2\\]CF3|\\[CH2\\]CCC|c1ccccc1|Si\\(CH3\\)3|c1ncncn1|\\[S\\]C\\(C\\)C|C1CCCCC1|C\\(=O\\)\\[O\\]|\\[AlH4\\-\\]|N\\(CH3\\)2|CC\\[CH2\\]|\\[BH\\]CH3|C1SCCN1|C1CCSC1|c1ccoc1|C\\(=O\\)SC|C1CCNC1|C1OCCN1|C1CCOC1|C1NCCN1|c1ccns1|C\\(=O\\)OC|C1SCCS1|C1OCOC1|c1ccno1|P\\(CH3\\)2|C\\(=O\\)Br|C\\(=O\\)Cl|CC\\(=O\\)O|c1ccsc1|\\[CH2\\]CN|c1cocn1|CS\\(=O\\)C|C\\[SiH2\\]|C\\(=O\\)SH|\\[PH\\]CC|P\\(=O\\)N|\\[81Br\\]|C1COC1|\\[BH4\\-\\]|\\[CH3\\-\\]|\\[35Cl\\]|\\[CH3\\+\\]|c1csn1|\\[C\\]Br3|C=CC\\#C|C\\(\\[O\\]\\)|\\[SiH2\\]|C\\(\\[C\\]\\)|\\[SiH4\\]|C=\\[CH\\]|\\[AlH2\\]|\\[79Br\\]|C1CNC1|\\[Fe\\+3\\]|\\[SnH3\\]|\\[Fe\\+2\\]|PO\\(C\\)C|CBrCl3|S\\(=O\\)N|C\\#CC\\#C|C\\#CC=C|PO\\(O\\)C|\\[Pt\\+2\\]|C\\(=N\\)N|CC\\[PH\\]|\\[C\\]Cl3|\\[CH4\\+\\]|\\[O\\]N=O|P\\(=O\\)O|\\[O\\]\\[O\\]|C\\[CH2\\]|C\\(=N\\)O|C1CSC1|\\[37Cl\\]|C\\(=O\\)I|\\[GeH3\\]|\\[Cu\\+1\\]|C\\(=S\\)N|C\\(=O\\)H|C\\(=O\\)N|\\[Pd\\+2\\]|C\\(\\[N\\]\\)|\\[SiH3\\]|C\\(=Si\\)|C\\(=O\\)O|CCCCCC|\\[GaH2\\]|\\[Cu\\+2\\]|C=CC=C|CHCl3|\\[12C\\]|\\[CH3\\]|CCOCC|\\[36S\\]|\\[16O\\]|C=C=C|\\[\\-\\-\\-\\]|C1NC1|NHCH3|C\\[PH\\]|\\[14C\\]|C1SC1|C\\(Cl\\)|\\[BH2\\]|C\\(=P\\)|\\[CH4\\]|\\[NH3\\]|\\[O\\]CC|CC\\[N\\]|\\[SeH\\]|SO2Cl|ClCCl|\\[CH2\\]|C\\(Br\\)|\\[PH2\\]|Si\\-Si|BrCBr|\\[S\\]CC|\\[NH4\\]|\\[13C\\]|\\[31P\\]|CC\\[O\\]|\\[PH3\\]|\\[O2\\-\\]|\\[NH2\\]|C\\(=O\\)|\\[15N\\]|PO3H2|\\[C@@\\]|N=C=S|N=C=O|\\[32S\\]|\\[S@@\\]|\\[34S\\]|\\[32P\\]|\\[33S\\]|CC\\[S\\]|C\\#\\[C\\]|C1CC1|\\[SiH\\]|C1OC1|\\[CH\\]N|\\[14N\\]|\\[17O\\]|\\[SH2\\]|\\[18O\\]|\\[P@@\\]|C\\(Si\\)|\\[OH2\\]|C\\(=S\\)|\\[N@@\\]|\\[35S\\]|Si=Si|\\[\\+\\+\\+\\]|C\\(S\\)|\\[C@\\]|C\\(B\\)|OCH3|\\[2H\\]|\\[Si\\]|CCl4|\\[N\\+\\]|CCCl|\\[PH\\]|\\[\\+1\\]|SCH3|CCCC|\\[\\-1\\]|\\[SH\\]|\\(CO\\)|Si\\-H|C\\(I\\)|CCF3|\\[3H\\]|C\\(P\\)|\\[\\-\\-\\]|\\[\\+\\+\\]|\\[NH\\]|\\[O\\-\\]|\\[P\\+\\]|C\\[S\\]|SO3H|\\[CH\\]|\\[oH\\]|SO2N|ICHI|\\[Se\\]|\\[S\\-\\]|CCl3|C\\-Si|\\[P@\\]|C\\[O\\]|CC\\#N|\\[OH\\]|C\\[N\\]|C\\(F\\)|\\[nH\\]|\\[S@\\]|\\[\\-2\\]|\\[N@\\]|C\\(O\\)|\\[cH\\]|C\\(C\\)|\\[O\\]O|C\\(N\\)|\\[C\\]N|\\[BH\\]|\\[\\+2\\]|CBr3|CCBr|\\[1H\\]|P\\-P|N\\-H|N\\#N|B\\-H|C\\#N|CCN|CCI|C\\-P|C\\-C|CCl|\\[p\\]|S\\-S|\\[\\+\\]|\\[n\\]|C\\#C|C=S|\\[C\\]|N=N|P\\-H|CCF|FCF|\\[S\\]|CI3|CF3|CCO|\\[\\*\\]|CCC|CSi|CCS|\\[c\\]|C=C|\\[D\\]|\\[T\\]|O\\-O|\\[\\-\\]|C\\-X|\\[s\\]|\\[B\\]|C\\-O|\\[P\\]|N\\-N|CBr|\\[R\\]|\\[X\\]|P=O|S\\-H|O\\-H|C=O|N\\#C|C\\-S|C=N|C\\-N|NO2|\\[o\\]|N=O|C\\-H|\\[N\\]|P=P|S=O|C\\-B|\\[O\\]|Cu|Be|Br|Mg|Pt|CO|Cd|Sn|Sr|Al|Co|CC|Li|Au|Rb|CN|Ca|Ge|In|Zr|CP|Fe|Hg|CS|Cl|CF|Cs|Te|Pd|Ba|Mn|Bi|Zn|Sb|Pb|As|Se|Na|Ag|Cr|Si|Ni|CI|Ga|Ti|F|O|H|C|K|P|V|S|\\*|B|N|I)"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "Split",
"pattern": {
"String": "(\\[.*?\\])"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "Split",
"pattern": {
"String": "(Cl|Br)"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "Split",
"pattern": {
"String": "(\\(|\\)|=|#|-|\\+|\\.)"
},
"behavior": "Isolated",
"invert": false
},
{
"type": "WhitespaceSplit"
}
]
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "</s>",
"type_id": 0
}
}
],
"special_tokens": {
"</s>": {
"id": "</s>",
"ids": [
3
],
"tokens": [
"</s>"
]
}
}
},
"decoder": {
"type": "BPEDecoder",
"suffix": "</w>"
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<unk>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<pad>": 0,
"<unk>": 1,
"<s>": 2,
"</s>": 3,
"#": 4,
"%": 5,
"(": 6,
")": 7,
"*": 8,
"+": 9,
"-": 10,
".": 11,
"/": 12,
"0": 13,
"1": 14,
"2": 15,
"3": 16,
"4": 17,
"5": 18,
"6": 19,
"7": 20,
"8": 21,
"9": 22,
":": 23,
"=": 24,
"@": 25,
"A": 26,
"B": 27,
"C": 28,
"D": 29,
"E": 30,
"F": 31,
"G": 32,
"H": 33,
"I": 34,
"J": 35,
"K": 36,
"L": 37,
"M": 38,
"N": 39,
"O": 40,
"P": 41,
"Q": 42,
"R": 43,
"S": 44,
"T": 45,
"U": 46,
"V": 47,
"W": 48,
"X": 49,
"Y": 50,
"Z": 51,
"[": 52,
"\\": 53,
"]": 54,
"a": 55,
"b": 56,
"c": 57,
"d": 58,
"e": 59,
"f": 60,
"g": 61,
"h": 62,
"i": 63,
"j": 64,
"k": 65,
"l": 66,
"m": 67,
"n": 68,
"o": 69,
"p": 70,
"q": 71,
"r": 72,
"s": 73,
"t": 74,
"u": 75,
"v": 76,
"w": 77,
"x": 78,
"y": 79,
"z": 80,
"{": 81,
"}": 82,
"CC": 83,
"C(": 84,
"O)": 85,
"C(C": 86,
"=O)": 87,
"C(C)": 88,
"CCC": 89,
"CO": 90,
"C(=O)": 91,
"C=": 92,
"cc": 93,
"CCCC": 94,
"C=C": 95,
"[C": 96,
"[CH": 97,
"[O": 98,
"-]": 99,
"[O-]": 100,
"[N": 101,
"+]": 102,
"[N+]": 103,
"[CH]": 104,
"C(=O)O": 105,
"C(O)": 106,
"c1": 107,
"CCO": 108,
"Cl": 109,
"(=O)": 110,
"(C": 111,
"N=": 112,
"N=O": 113,
"2]": 114,
"[CH2]": 115,
"CC(=O)": 116,
"Br": 117,
"CC(=O)O": 118,
"cccc": 119,
"c1cccc": 120,
"C=O": 121,
"c1ccccc1": 122,
"(CO)": 123,
"C1": 124,
"C(=O)OC": 125,
"l)": 126,
"C(Cl)": 127,
"CCCCCC": 128,
"CCl": 129,
"(C)": 130,
"OO": 131,
"C#": 132,
"CC(=O)OC": 133,
"C=CC": 134,
"OC1": 135,
"C1OC1": 136,
"CN": 137,
"=C": 138,
"CS": 139,
"C#N": 140,
"C=CC=C": 141,
"C1CC": 142,
"(=O)[O-]": 143,
"[N+](=O)[O-]": 144,
"CCC1": 145,
"CBr": 146,
"F)": 147,
"CCN": 148,
"CC(": 149,
"Br)": 150,
"CC(C)": 151,
"C(F)": 152,
"C(Br)": 153,
"CC1": 154,
"C1CCCCC1": 155,
"CCCl": 156,
"O[N+](=O)[O-]": 157,
"CCS": 158,
"Si": 159,
"C#C": 160,
"[CH2]C=C": 161,
"S(=O)": 162,
"S(=O)(=O)": 163,
"C2": 164,
"C(=O)N": 165,
"Sn": 166,
"[CH2]CCC": 167,
"C(=": 168,
"CCOCC": 169,
"N=N": 170,
"c1ccccc1C": 171,
"C(C)(C)": 172,
"O=": 173,
"OO)": 174,
"#N": 175,
"(O)": 176,
"[Si": 177,
"C1CC1": 178,
"S)": 179,
"C(=S)": 180,
"[Si]": 181,
"c2": 182,
"O[N+](=O)[O-])": 183,
"Cl)": 184,
"CC#N": 185,
"Na": 186,
"#C": 187,
"H]": 188,
"N#C": 189,
"CCBr": 190,
"=O": 191,
"CC(O)": 192,
"OOO": 193,
"CO[N+](=O)[O-]": 194,
"N)": 195,
"COO": 196,
"CC(C)(C)": 197,
"(OO)": 198,
"[C@": 199,
"(C)C": 200,
"=CC": 201,
"CC)": 202,
"C[CH]": 203,
"c1cc": 204,
"C2O": 205,
"(OO": 206,
"CCC(C)": 207,
"C=C(C)": 208,
"OON=O": 209,
"C(CO)": 210,
"[O-])": 211,
"(Cl)": 212,
"/C=C": 213,
"CCCC1": 214,
"C)": 215,
"([O-])": 216,
"N=O)": 217,
"CC(Cl)": 218,
"=C(C)": 219,
"CC(C": 220,
"COOO": 221,
"OOO[N+](=O)[O-]": 222,
"ccccc2": 223,
"1)": 224,
"C(OO": 225,
"c2ccccc2": 226,
"[N+]([O-])": 227,
"c1ccccc1)": 228,
"N)N": 229,
"[C@]": 230,
"[S": 231,
"C=N": 232,
"CCCCCCCC": 233,
"C(=N)N": 234,
"O=[N+]([O-])": 235,
"[CH]N": 236,
"CO[N+](=O)[O-])": 237,
"CC(CO)": 238,
"C=C1": 239,
"COCCO": 240,
"CC1(C)": 241,
"C(C)(C)C": 242,
"C(N)": 243,
"C=CC(C)": 244,
"Mg": 245,
"C(C)=O": 246,
"[SH]": 247,
"COCCO1": 248,
"c(": 249,
"C=C=C": 250,
"C1COCCO1": 251,
"CCC(=O)": 252,
"cc1": 253,
"/C=C\\": 254,
"COC(=O)": 255,
"C(=O)OO": 256,
"1)C2O": 257,
"CC12": 258,
"I)": 259,
"C1O": 260,
"(CC)": 261,
"C1C2": 262,
"CC(C)(O)": 263,
"(CO[N+](=O)[O-])": 264,
"C(C)O": 265,
"CCC(": 266,
"C(I)": 267,
"COO)": 268,
"N1": 269,
"[CH2]C(=O)O": 270,
"CI": 271,
"C(C=O)": 272,
"CC(C=O)": 273,
"(O[N+](=O)[O-])": 274,
"Cc1cc": 275,
"OC": 276,
"c(O)": 277,
"C1(C)": 278,
"C=CC1": 279,
"C(=O)N(C)C": 280,
"COON=O": 281,
"COOO[N+](=O)[O-]": 282,
"CCC2": 283,
"CCCC(C)": 284,
"O=N": 285,
"C(=O)OC)": 286,
"(Cl)Cl": 287,
"=CC1": 288,
"c3": 289,
"CCOO": 290,
"C(=C": 291,
"C(C)C": 292,
"CCC12": 293,
"CC1=": 294,
"CC1(C)C2": 295,
"CCC(O)": 296,
"=C1": 297,
"CC[CH]": 298,
"C(C)(OO": 299,
"c1ccccc1)c1ccccc1": 300,
"O=NOO": 301,
"(F)": 302,
"C/": 303,
"CC2": 304,
"C=CC2": 305,
"CC1=CC": 306,
"CCCCC1": 307,
"C(F)(F)": 308,
"C(CO)OO": 309,
"C(OO1)C2O": 310,
"c2ccccc2)": 311,
"(Br)": 312,
"Cc1ccccc1": 313,
"CCC(C": 314,
"CCOC(=O)": 315,
"[CH2]C(=O)": 316,
"/C=C/": 317,
"O=[N+]([O-])O": 318,
"CCCCC": 319,
"CCCCO": 320,
"OC)": 321,
"[n": 322,
"CC=": 323,
"[CH2]c1ccccc1": 324,
"#N)": 325,
"[nH]": 326,
"[CH]O": 327,
"[CH]O)": 328,
"[CH2]C(=O)OC": 329,
"CC(C)O": 330,
"C(C)(C)O": 331,
"C(OO)": 332,
"C(CC)": 333,
"CC(C)(C)O": 334,
"(OON=O)": 335,
"[CH2]C(=O)C": 336,
"2)": 337,
"C(C)(O)": 338,
"CCOOO": 339,
"O=[N+]([O-])OOO": 340,
"c(C)": 341,
"[CH]1": 342,
"C(O)CO": 343,
"CC(O)(": 344,
"(CC": 345,
"C(C)O[N+](=O)[O-]": 346,
"C(=O)OCC": 347,
"CC(=": 348,
"CC(OO": 349,
"[C@H]": 350,
"C/C(=C": 351,
"(O": 352,
"CO)": 353,
"(C=O)": 354,
"OC1(C)": 355,
"CCCC(=O)": 356,
"C2(C)": 357,
"C(C)(C)C)": 358,
"O=C1": 359,
"c2ccccc21": 360,
"OC(C)=O": 361,
"C(Cl)(Cl)": 362,
"C12": 363,
"C(Cl)Cl": 364,
"C1CC2": 365,
"CC(CO[N+](=O)[O-])": 366,
"CC1=C(C)": 367,
"C=C(C)C1CC": 368,
"C(C=O)OO": 369,
"C(O[N+](=O)[O-])": 370,
"CCC=C(C)": 371,
"C=C(": 372,
"CCCC)": 373,
"CCCC2": 374,
"C=C[CH]": 375,
"C(O)COO": 376,
"OOC1": 377,
"C=CC=CC1": 378,
"CC(OO)": 379,
"C(CO[N+](=O)[O-])": 380,
"CO1": 381,
"C=CCC1": 382,
"OOC(C)": 383,
"C(COO)": 384,
"C(O)C(C)": 385,
"CCOC1": 386,
"(C#N)": 387,
"ccccc3": 388,
"C1=": 389,
"C#CCCC": 390,
"C=CC(O)": 391,
"CC(C)=": 392,
"[Si](C)": 393,
"CC(Cl)CC(Cl)": 394,
"CC(CO)(OO)": 395,
"N1CCCC1": 396,
"CCC2C1CC2": 397,
"c3ccccc3": 398,
"CCC2C1CC2(C)C": 399,
"Cc1cccc": 400,
"[Sn": 401,
"CCC(C)(C)": 402,
"C(C)=O)": 403,
"C(C)OO": 404,
"CC(CC(": 405,
"CC(C)(C#N)": 406,
"C2(C)C": 407,
"(OOO)": 408,
"(OOO[N+](=O)[O-])": 409,
"C(CO)O[N+](=O)[O-]": 410,
"c(OC)": 411,
"SC": 412,
"CCC(OO": 413,
"CCCC(O)": 414,
"OOC1(C)": 415,
"CC(O[N+](=O)[O-])": 416,
"CC(C)(C)OO": 417,
"CC(C[CH]": 418,
"CC1=CCC(": 419,
"(CCCC)": 420,
"C(O)C=O": 421,
"CC(=C": 422,
"CCCCCCCCCCCC": 423,
"[Sn]": 424,
"OOC1(C)C2O": 425,
"(C(=O)O": 426,
"(C(=O)OC)": 427,
"3]": 428,
"N#N": 429,
"OCCO": 430,
"S=O": 431,
"ncc1": 432,
"CCI": 433,
"C(C)OOO": 434,
"C(=O)SC": 435,
"[CH3]": 436,
"[OH]": 437,
"ClCCl": 438,
"[CH2]C(C)": 439,
"C1CCOC1": 440,
"C1OC1(C)": 441,
"CC(=CC": 442,
"[SiH]": 443,
"COON=O)": 444,
"c1ccncc1": 445,
"[S-]": 446,
"CC(C=O)(OO)": 447,
"C/C(=C/": 448,
"C#CCCC[CH2]": 449,
"CC(C)(C)OOC(C)(C)C": 450,
"CF": 451,
"C[CH2]": 452,
"CC[CH2]": 453,
"C(O": 454,
"O)OO": 455,
"C(C)OON=O": 456,
"COCO": 457,
"COC(=O)OO": 458,
"[Na": 459,
"ClC1": 460,
"C1OC1C=O": 461,
"CSC(=S)": 462,
"CC(CC": 463,
"CC1(": 464,
"CC1C2(C)C": 465,
"[CH2]CCC=CC": 466,
"C(C)(C)OO": 467,
"CC(O)(CO[N+](=O)[O-])": 468,
"(C)C)": 469,
"C(CO)OON=O": 470,
"c(O)c1": 471,
"C=CC2OOC1(C)C2O": 472,
"C(F)(F)C(F)": 473,
"COC(=O)OOC(=O)OC": 474,
"CSC(=S)OC": 475,
"(COO)": 476,
"@H]": 477,
"n1": 478,
"C(C)OOO[N+](=O)[O-]": 479,
"CCC=": 480,
"(C1": 481,
"C1=C": 482,
"C(Cl)(Cl)Cl": 483,
"CCCCCCCCC": 484,
"(C)cc": 485,
"[C@@H]": 486,
"c1ccc(": 487,
"CCC(O[N+](=O)[O-])": 488,
"CCOOO[N+](=O)[O-]": 489,
"/C=C(": 490,
"2(C)": 491,
"OCC": 492,
"[CH]CO": 493,
"CC(=O)C(O)": 494,
"CCC1=C(C)": 495,
"CC(C)=O": 496,
"C(C)(C)O[N+](=O)[O-]": 497,
"CCCCCCCC(=O)": 498,
"Cc1ccc(": 499,
"OOC1C2O": 500,
"OOC(C)(C1": 501,
"[Na]": 502,
"(CO": 503,
"(c1ccccc1)c1ccccc1": 504,
"C/C=C\\": 505,
"CCC(CO)": 506,
"C(COO": 507,
"C=CCC": 508,
"C=CCCC1": 509,
"C(O)OO": 510,
"CCO[N+](=O)[O-]": 511
},
"merges": [
[
"C",
"C"
],
[
"C",
"("
],
[
"O",
")"
],
[
"C(",
"C"
],
[
"=",
"O)"
],
[
"C(C",
")"
],
[
"CC",
"C"
],
[
"C",
"O"
],
[
"C(",
"=O)"
],
[
"C",
"="
],
[
"c",
"c"
],
[
"CC",
"CC"
],
[
"C=",
"C"
],
[
"[",
"C"
],
[
"[C",
"H"
],
[
"[",
"O"
],
[
"-",
"]"
],
[
"[O",
"-]"
],
[
"[",
"N"
],
[
"+",
"]"
],
[
"[N",
"+]"
],
[
"[CH",
"]"
],
[
"C(=O)",
"O"
],
[
"C(",
"O)"
],
[
"c",
"1"
],
[
"CC",
"O"
],
[
"C",
"l"
],
[
"(",
"=O)"
],
[
"(",
"C"
],
[
"N",
"="
],
[
"N=",
"O"
],
[
"2",
"]"
],
[
"[CH",
"2]"
],
[
"CC",
"(=O)"
],
[
"B",
"r"
],
[
"CC(=O)",
"O"
],
[
"cc",
"cc"
],
[
"c1",
"cccc"
],
[
"C=",
"O"
],
[
"c1cccc",
"c1"
],
[
"(C",
"O)"
],
[
"C",
"1"
],
[
"C(=O)O",
"C"
],
[
"l",
")"
],
[
"C(C",
"l)"
],
[
"CCCC",
"CC"
],
[
"CC",
"l"
],
[
"(C",
")"
],
[
"O",
"O"
],
[
"C",
"#"
],
[
"CC(=O)O",
"C"
],
[
"C=",
"CC"
],
[
"O",
"C1"
],
[
"C1",
"OC1"
],
[
"C",
"N"
],
[
"=",
"C"
],
[
"C",
"S"
],
[
"C#",
"N"
],
[
"C=CC",
"=C"
],
[
"C1",
"CC"
],
[
"(=O)",
"[O-]"
],
[
"[N+]",
"(=O)[O-]"
],
[
"CCC",
"1"
],
[
"C",
"Br"
],
[
"F",
")"
],
[
"CC",
"N"
],
[
"CC",
"("
],
[
"Br",
")"
],
[
"CC",
"(C)"
],
[
"C(",
"F)"
],
[
"C(",
"Br)"
],
[
"CC",
"1"
],
[
"C1CC",
"CCC1"
],
[
"CCC",
"l"
],
[
"O",
"[N+](=O)[O-]"
],
[
"CC",
"S"
],
[
"S",
"i"
],
[
"C#",
"C"
],
[
"[CH2]",
"C=C"
],
[
"S",
"(=O)"
],
[
"S(=O)",
"(=O)"
],
[
"C",
"2"
],
[
"C(=O)",
"N"
],
[
"S",
"n"
],
[
"[CH2]",
"CCC"
],
[
"C(",
"="
],
[
"CCO",
"CC"
],
[
"N=",
"N"
],
[
"c1ccccc1",
"C"
],
[
"C(C)",
"(C)"
],
[
"O",
"="
],
[
"O",
"O)"
],
[
"#",
"N"
],
[
"(",
"O)"
],
[
"[",
"Si"
],
[
"C1CC",
"1"
],
[
"S",
")"
],
[
"C(=",
"S)"
],
[
"[Si",
"]"
],
[
"c",
"2"
],
[
"O[N+](=O)[O-]",
")"
],
[
"Cl",
")"
],
[
"CC",
"#N"
],
[
"N",
"a"
],
[
"#",
"C"
],
[
"H",
"]"
],
[
"N",
"#C"
],
[
"CC",
"Br"
],
[
"=",
"O"
],
[
"CC(",
"O)"
],
[
"OO",
"O"
],
[
"CO",
"[N+](=O)[O-]"
],
[
"N",
")"
],
[
"CO",
"O"
],
[
"CC(C)",
"(C)"
],
[
"(",
"OO)"
],
[
"[C",
"@"
],
[
"(C)",
"C"
],
[
"=",
"CC"
],
[
"CC",
")"
],
[
"C",
"[CH]"
],
[
"c1",
"cc"
],
[
"C2",
"O"
],
[
"(",
"OO"
],
[
"CC",
"C(C)"
],
[
"C=",
"C(C)"
],
[
"OO",
"N=O"
],
[
"C(C",
"O)"
],
[
"[O-]",
")"
],
[
"(",
"Cl)"
],
[
"/",
"C=C"
],
[
"CCCC",
"1"
],
[
"C",
")"
],
[
"(",
"[O-])"
],
[
"N",
"=O)"
],
[
"CC(",
"Cl)"
],
[
"=",
"C(C)"
],
[
"CC",
"(C"
],
[
"CO",
"OO"
],
[
"OO",
"O[N+](=O)[O-]"
],
[
"cccc",
"c2"
],
[
"1",
")"
],
[
"C(",
"OO"
],
[
"c2",
"ccccc2"
],
[
"[N+]",
"([O-])"
],
[
"c1ccccc1",
")"
],
[
"N)",
"N"
],
[
"[C@",
"]"
],
[
"[",
"S"
],
[
"C=",
"N"
],
[
"CCCC",
"CCCC"
],
[
"C(=",
"N)N"
],
[
"O=",
"[N+]([O-])"
],
[
"[CH]",
"N"
],
[
"CO[N+](=O)[O-]",
")"
],
[
"CC",
"(CO)"
],
[
"C=C",
"1"
],
[
"CO",
"CCO"
],
[
"CC1",
"(C)"
],
[
"C(C)(C)",
"C"
],
[
"C(",
"N)"
],
[
"C=CC",
"(C)"
],
[
"M",
"g"
],
[
"C(C)",
"=O"
],
[
"[S",
"H]"
],
[
"COCCO",
"1"
],
[
"c",
"("
],
[
"C=",
"C=C"
],
[
"C1",
"COCCO1"
],
[
"CC",
"C(=O)"
],
[
"cc",
"1"
],
[
"/C=C",
"\\"
],
[
"CO",
"C(=O)"
],
[
"C(=O)O",
"O"
],
[
"1)",
"C2O"
],
[
"CC1",
"2"
],
[
"I",
")"
],
[
"C1",
"O"
],
[
"(",
"CC)"
],
[
"C1",
"C2"
],
[
"CC(C)",
"(O)"
],
[
"(",
"CO[N+](=O)[O-])"
],
[
"C(C)",
"O"
],
[
"CC",
"C("
],
[
"C(",
"I)"
],
[
"CO",
"O)"
],
[
"N",
"1"
],
[
"[CH2]",
"C(=O)O"
],
[
"C",
"I"
],
[
"C(C",
"=O)"
],
[
"CC(C",
"=O)"
],
[
"(",
"O[N+](=O)[O-])"
],
[
"C",
"c1cc"
],
[
"O",
"C"
],
[
"c",
"(O)"
],
[
"C1",
"(C)"
],
[
"C=CC",
"1"
],
[
"C(=O)N",
"(C)C"
],
[
"COO",
"N=O"
],
[
"COOO",
"[N+](=O)[O-]"
],
[
"CCC",
"2"
],
[
"CCCC",
"(C)"
],
[
"O=",
"N"
],
[
"C(=O)OC",
")"
],
[
"(Cl)",
"Cl"
],
[
"=",
"CC1"
],
[
"c",
"3"
],
[
"CCO",
"O"
],
[
"C(",
"=C"
],
[
"C(C)",
"C"
],
[
"CCC1",
"2"
],
[
"CC1",
"="
],
[
"CC1(C)",
"C2"
],
[
"CC",
"C(O)"
],
[
"=",
"C1"
],
[
"CC",
"[CH]"
],
[
"C(C)",
"(OO"
],
[
"c1ccccc1)",
"c1ccccc1"
],
[
"O=N",
"OO"
],
[
"(",
"F)"
],
[
"C",
"/"
],
[
"CC",
"2"
],
[
"C=CC",
"2"
],
[
"CC1",
"=CC"
],
[
"CC",
"CCC1"
],
[
"C(F)",
"(F)"
],
[
"C(CO)",
"OO"
],
[
"C(OO",
"1)C2O"
],
[
"c2ccccc2",
")"
],
[
"(",
"Br)"
],
[
"C",
"c1ccccc1"
],
[
"CC",
"C(C"
],
[
"CCO",
"C(=O)"
],
[
"[CH2]",
"C(=O)"
],
[
"/C=C",
"/"
],
[
"O=[N+]([O-])",
"O"
],
[
"CC",
"CCC"
],
[
"CCCC",
"O"
],
[
"O",
"C)"
],
[
"[",
"n"
],
[
"CC",
"="
],
[
"[CH2]",
"c1ccccc1"
],
[
"#N",
")"
],
[
"[n",
"H]"
],
[
"[CH]",
"O"
],
[
"[CH]",
"O)"
],
[
"[CH2]",
"C(=O)OC"
],
[
"CC(C)",
"O"
],
[
"C(C)(C)",
"O"
],
[
"C(",
"OO)"
],
[
"C(",
"CC)"
],
[
"CC(C)(C)",
"O"
],
[
"(OO",
"N=O)"
],
[
"[CH2]C(=O)",
"C"
],
[
"2",
")"
],
[
"C(C)",
"(O)"
],
[
"CCO",
"OO"
],
[
"O=[N+]([O-])",
"OOO"
],
[
"c",
"(C)"
],
[
"[CH]",
"1"
],
[
"C(O)",
"CO"
],
[
"CC(O)",
"("
],
[
"(",
"CC"
],
[
"C(C)",
"O[N+](=O)[O-]"
],
[
"C(=O)O",
"CC"
],
[
"CC(",
"="
],
[
"CC(",
"OO"
],
[
"[C@",
"H]"
],
[
"C/",
"C(=C"
],
[
"(",
"O"
],
[
"C",
"O)"
],
[
"(C",
"=O)"
],
[
"OC1",
"(C)"
],
[
"CCCC",
"(=O)"
],
[
"C2",
"(C)"
],
[
"C(C)(C)",
"C)"
],
[
"O=",
"C1"
],
[
"c2ccccc2",
"1"
],
[
"O",
"C(C)=O"
],
[
"C(Cl)",
"(Cl)"
],
[
"C1",
"2"
],
[
"C(Cl)",
"Cl"
],
[
"C1CC",
"2"
],
[
"CC(",
"CO[N+](=O)[O-])"
],
[
"CC1",
"=C(C)"
],
[
"C=C(C)",
"C1CC"
],
[
"C(C=O)",
"OO"
],
[
"C(",
"O[N+](=O)[O-])"
],
[
"CCC",
"=C(C)"
],
[
"C=",
"C("
],
[
"CCCC",
")"
],
[
"CCCC",
"2"
],
[
"C=C",
"[CH]"
],
[
"C(O)",
"COO"
],
[
"OO",
"C1"
],
[
"C=CC",
"=CC1"
],
[
"CC(",
"OO)"
],
[
"C(C",
"O[N+](=O)[O-])"
],
[
"CO",
"1"
],
[
"C=",
"CCC1"
],
[
"OO",
"C(C)"
],
[
"C(C",
"OO)"
],
[
"C(O)",
"C(C)"
],
[
"CCO",
"C1"
],
[
"(C",
"#N)"
],
[
"cccc",
"c3"
],
[
"C1",
"="
],
[
"C#",
"CCCC"
],
[
"C=CC",
"(O)"
],
[
"CC(C)",
"="
],
[
"[Si]",
"(C)"
],
[
"CC(Cl)",
"CC(Cl)"
],
[
"CC(CO)",
"(OO)"
],
[
"N1",
"CCCC1"
],
[
"CCC2",
"C1CC2"
],
[
"c3",
"ccccc3"
],
[
"CCC2C1CC2",
"(C)C"
],
[
"C",
"c1cccc"
],
[
"[",
"Sn"
],
[
"CC",
"C(C)(C)"
],
[
"C(C)",
"=O)"
],
[
"C(C)",
"OO"
],
[
"CC(",
"CC("
],
[
"CC(C)",
"(C#N)"
],
[
"C2",
"(C)C"
],
[
"(OO",
"O)"
],
[
"(OO",
"O[N+](=O)[O-])"
],
[
"C(CO)",
"O[N+](=O)[O-]"
],
[
"c(",
"OC)"
],
[
"S",
"C"
],
[
"CC",
"C(OO"
],
[
"CCCC",
"(O)"
],
[
"OO",
"C1(C)"
],
[
"CC(",
"O[N+](=O)[O-])"
],
[
"CC(C)(C)",
"OO"
],
[
"CC(C",
"[CH]"
],
[
"CC1=CC",
"C("
],
[
"(",
"CCCC)"
],
[
"C(O)",
"C=O"
],
[
"CC(",
"=C"
],
[
"CCCCCCCC",
"CCCC"
],
[
"[Sn",
"]"
],
[
"OOC1(C)",
"C2O"
],
[
"(",
"C(=O)O"
],
[
"(",
"C(=O)OC)"
],
[
"3",
"]"
],
[
"N",
"#N"
],
[
"O",
"CCO"
],
[
"S",
"=O"
],
[
"n",
"cc1"
],
[
"CC",
"I"
],
[
"C(C)",
"OOO"
],
[
"C(=O)",
"SC"
],
[
"[CH",
"3]"
],
[
"[O",
"H]"
],
[
"Cl",
"CCl"
],
[
"[CH2]",
"C(C)"
],
[
"C1",
"CCOC1"
],
[
"C1OC1",
"(C)"
],
[
"CC(",
"=CC"
],
[
"[Si",
"H]"
],
[
"COO",
"N=O)"
],
[
"c1cc",
"ncc1"
],
[
"[S",
"-]"
],
[
"CC(C=O)",
"(OO)"
],
[
"C/C(=C",
"/"
],
[
"C#CCCC",
"[CH2]"
],
[
"CC(C)(C)OO",
"C(C)(C)C"
],
[
"C",
"F"
],
[
"C",
"[CH2]"
],
[
"CC",
"[CH2]"
],
[
"C(",
"O"
],
[
"O)",
"OO"
],
[
"C(C)",
"OON=O"
],
[
"CO",
"CO"
],
[
"CO",
"C(=O)OO"
],
[
"[N",
"a"
],
[
"Cl",
"C1"
],
[
"C1OC1",
"C=O"
],
[
"CS",
"C(=S)"
],
[
"CC(",
"CC"
],
[
"CC1",
"("
],
[
"CC1",
"C2(C)C"
],
[
"[CH2]CCC",
"=CC"
],
[
"C(C)(C)",
"OO"
],
[
"CC(O)",
"(CO[N+](=O)[O-])"
],
[
"(C)C",
")"
],
[
"C(CO)",
"OON=O"
],
[
"c(O)",
"c1"
],
[
"C=CC2",
"OOC1(C)C2O"
],
[
"C(F)(F)",
"C(F)"
],
[
"COC(=O)OO",
"C(=O)OC"
],
[
"CSC(=S)",
"OC"
],
[
"(",
"COO)"
],
[
"@",
"H]"
],
[
"n",
"1"
],
[
"C(C)",
"OOO[N+](=O)[O-]"
],
[
"CCC",
"="
],
[
"(C",
"1"
],
[
"C1",
"=C"
],
[
"C(Cl)",
"(Cl)Cl"
],
[
"CCCCCC",
"CCC"
],
[
"(C)",
"cc"
],
[
"[C@",
"@H]"
],
[
"c1cc",
"c("
],
[
"CCC(",
"O[N+](=O)[O-])"
],
[
"CCOOO",
"[N+](=O)[O-]"
],
[
"/",
"C=C("
],
[
"2",
"(C)"
],
[
"O",
"CC"
],
[
"[CH]",
"CO"
],
[
"CC(=O)",
"C(O)"
],
[
"CCC1",
"=C(C)"
],
[
"CC(C)",
"=O"
],
[
"C(C)(C)",
"O[N+](=O)[O-]"
],
[
"CCCCCCCC",
"(=O)"
],
[
"Cc1cc",
"c("
],
[
"OOC1",
"C2O"
],
[
"OOC(C)",
"(C1"
],
[
"[Na",
"]"
],
[
"(",
"CO"
],
[
"(",
"c1ccccc1)c1ccccc1"
],
[
"C",
"/C=C\\"
],
[
"CC",
"C(CO)"
],
[
"C(C",
"OO"
],
[
"C=",
"CCC"
],
[
"C=",
"CCCC1"
],
[
"C(O)",
"OO"
],
[
"CCO",
"[N+](=O)[O-]"
]
]
}
}