Files
Franso-reinvent_229M_256_prior/tokenizer.json

1199 lines
15 KiB
JSON
Raw Normal View History

{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 256,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 257,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 258,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 259,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "\\(|\\)"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": null,
"decoder": {
"type": "BPEDecoder",
"suffix": "</w>"
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"#": 0,
"%": 1,
"(": 2,
")": 3,
"+": 4,
"-": 5,
"/": 6,
"0": 7,
"1": 8,
"2": 9,
"3": 10,
"4": 11,
"5": 12,
"6": 13,
"7": 14,
"8": 15,
"9": 16,
"=": 17,
"@": 18,
"B": 19,
"C": 20,
"F": 21,
"H": 22,
"I": 23,
"N": 24,
"O": 25,
"P": 26,
"S": 27,
"[": 28,
"\\": 29,
"]": 30,
"c": 31,
"i": 32,
"l": 33,
"n": 34,
"o": 35,
"r": 36,
"s": 37,
"cc": 38,
"CC": 39,
"c1": 40,
"=O": 41,
"c2": 42,
"H]": 43,
"[C": 44,
"[C@": 45,
"c1cc": 46,
"[C@@": 47,
"c3": 48,
"c2cc": 49,
"[C@H]": 50,
"[C@@H]": 51,
"NC": 52,
"c1ccc": 53,
"CCC": 54,
"CO": 55,
"cc1": 56,
"=C": 57,
"c1cccc": 58,
"n1": 59,
"N1": 60,
"nc": 61,
"c2cccc": 62,
"OC": 63,
"c3cc": 64,
"Cl": 65,
"C1": 66,
"N2": 67,
"CCN": 68,
"CC1": 69,
"c2ccccc2": 70,
"c2ccc": 71,
"n2": 72,
"O=C": 73,
"c1ccccc1": 74,
"C2": 75,
"CC2": 76,
"CN": 77,
"cc2": 78,
"CCO": 79,
"[C@@H]1": 80,
"C[C@H]": 81,
"c3cccc": 82,
"[n": 83,
"[nH]": 84,
"c1n": 85,
"cn": 86,
"c4": 87,
"[C@@H]2": 88,
"[C@H]1": 89,
"c3ccccc3": 90,
"Cc1ccc": 91,
"CCCC": 92,
"c2c": 93,
"[C@H]2": 94,
"COc1ccc": 95,
"/C": 96,
"c2n": 97,
"C[C@@H]": 98,
"Cc1cc": 99,
"c1c": 100,
"c3ccc": 101,
"CNC": 102,
"cccc": 103,
"n3": 104,
"CS": 105,
"nc1": 106,
"COC": 107,
"+]": 108,
"Br": 109,
"cc3": 110,
"N1CCC": 111,
"C3": 112,
"[N": 113,
"[N+]": 114,
"-]": 115,
"[O": 116,
"[O-]": 117,
"s1": 118,
"c1nc": 119,
"nc2": 120,
"N1C": 121,
"CCOC": 122,
"o1": 123,
"CCCCC": 124,
"CC3": 125,
"CCCN": 126,
"[C@]": 127,
"ccc1": 128,
"[C@@]": 129,
"OCC": 130,
"Cn1": 131,
"c3c": 132,
"N3": 133,
"N1CC": 134,
"Cc1n": 135,
"ccc": 136,
"NCC": 137,
"CN2": 138,
"N1CCN": 139,
"c2nc": 140,
"c1C": 141,
"=S": 142,
"=N": 143,
"C[C@@H]1": 144,
"COc1cc": 145,
"Nc1ccc": 146,
"/C=C": 147,
"o2": 148,
"CCCO": 149,
"C#": 150,
"C[C@H]1": 151,
"Cc1ccccc1": 152,
"ccc2": 153,
"s2": 154,
"[C@H]3": 155,
"[C@@H]3": 156,
"N2CCC": 157,
"Cc1cccc": 158,
"c4cccc": 159,
"c1cn": 160,
"oc": 161,
"CCNC": 162,
"sc": 163,
"nn": 164,
"N2C": 165,
"-c2ccc": 166,
"C#N": 167,
"N2CC": 168,
"Cc1c": 169,
"CCS": 170,
"CCn1": 171,
"C1=O": 172,
"C2=O": 173,
"cc1C": 174,
"[nH]c": 175,
"O=C1": 176,
"-c2ccccc2": 177,
"N=C": 178,
"Cc2ccccc2": 179,
"c12": 180,
"N2CCN": 181,
"CC[C@H]": 182,
"CC[C@@H]": 183,
"c4ccccc4": 184,
"C[C@H]2": 185,
"c1=O": 186,
"NS": 187,
"Cc1nc": 188,
"c1ccc2c": 189,
"NC1": 190,
"COc1cccc": 191,
"Nc2ccc": 192,
"c3n": 193,
"cn1": 194,
"[nH]1": 195,
"C=": 196,
"COc1ccccc1": 197,
"c2ccccc21": 198,
"c2cn": 199,
"N[C@H]": 200,
"N[C@@H]": 201,
"c1nnc": 202,
"c2c1": 203,
"CCOc1ccc": 204,
"SCC": 205,
"CCOCC2": 206,
"OCO": 207,
"c3nc": 208,
"c1ncc": 209,
"Cc2ccc": 210,
"cc1OC": 211,
"NC2": 212,
"nc3": 213,
"CCCCC2": 214,
"C=C": 215,
"N1CCO": 216,
"nn1": 217,
"[C@]1": 218,
"CCCC2": 219,
"-n2": 220,
"c2ncc": 221,
"C[C@@H]2": 222,
"cc1Cl": 223,
"Nc1cccc": 224,
"c2nnc": 225,
"[C@@]1": 226,
"CCCC3": 227,
"CCCCC1": 228,
"c2ccc3c": 229,
"-c3ccccc3": 230,
"nn2": 231,
"c4ccc": 232,
"CCC2": 233,
"no1": 234,
"OCCO": 235,
"O1": 236,
"Cn2": 237,
"SC": 238,
"-c3ccc": 239,
"Nc1cc": 240,
"/C=C/": 241,
"Cn1cc": 242,
"N[C@@H]1": 243,
"c23": 244,
"Nc1ccccc1": 245,
"N#": 246,
"CN1C": 247,
"[C@@]2": 248,
"[C@]2": 249,
"C2CC2": 250,
"c2C": 251,
"o3": 252,
"NCCC": 253,
"N2CCOCC2": 254,
"N[C@H]1": 255
},
"merges": [
[
"c",
"c"
],
[
"C",
"C"
],
[
"c",
"1"
],
[
"=",
"O"
],
[
"c",
"2"
],
[
"H",
"]"
],
[
"[",
"C"
],
[
"[C",
"@"
],
[
"c1",
"cc"
],
[
"[C@",
"@"
],
[
"c",
"3"
],
[
"c2",
"cc"
],
[
"[C@",
"H]"
],
[
"[C@@",
"H]"
],
[
"N",
"C"
],
[
"c1cc",
"c"
],
[
"CC",
"C"
],
[
"C",
"O"
],
[
"cc",
"1"
],
[
"=",
"C"
],
[
"c1cc",
"cc"
],
[
"n",
"1"
],
[
"N",
"1"
],
[
"n",
"c"
],
[
"c2cc",
"cc"
],
[
"O",
"C"
],
[
"c3",
"cc"
],
[
"C",
"l"
],
[
"C",
"1"
],
[
"N",
"2"
],
[
"CC",
"N"
],
[
"CC",
"1"
],
[
"c2cccc",
"c2"
],
[
"c2cc",
"c"
],
[
"n",
"2"
],
[
"O",
"=C"
],
[
"c1cccc",
"c1"
],
[
"C",
"2"
],
[
"CC",
"2"
],
[
"C",
"N"
],
[
"cc",
"2"
],
[
"CC",
"O"
],
[
"[C@@H]",
"1"
],
[
"C",
"[C@H]"
],
[
"c3cc",
"cc"
],
[
"[",
"n"
],
[
"[n",
"H]"
],
[
"c1",
"n"
],
[
"c",
"n"
],
[
"c",
"4"
],
[
"[C@@H]",
"2"
],
[
"[C@H]",
"1"
],
[
"c3cccc",
"c3"
],
[
"C",
"c1ccc"
],
[
"CC",
"CC"
],
[
"c2",
"c"
],
[
"[C@H]",
"2"
],
[
"CO",
"c1ccc"
],
[
"/",
"C"
],
[
"c2",
"n"
],
[
"C",
"[C@@H]"
],
[
"C",
"c1cc"
],
[
"c1",
"c"
],
[
"c3cc",
"c"
],
[
"C",
"NC"
],
[
"cc",
"cc"
],
[
"n",
"3"
],
[
"C",
"S"
],
[
"n",
"c1"
],
[
"CO",
"C"
],
[
"+",
"]"
],
[
"B",
"r"
],
[
"cc",
"3"
],
[
"N1",
"CCC"
],
[
"C",
"3"
],
[
"[",
"N"
],
[
"[N",
"+]"
],
[
"-",
"]"
],
[
"[",
"O"
],
[
"[O",
"-]"
],
[
"s",
"1"
],
[
"c1",
"nc"
],
[
"n",
"c2"
],
[
"N1",
"C"
],
[
"CC",
"OC"
],
[
"o",
"1"
],
[
"CC",
"CCC"
],
[
"CC",
"3"
],
[
"CCC",
"N"
],
[
"[C@",
"]"
],
[
"cc",
"c1"
],
[
"[C@@",
"]"
],
[
"O",
"CC"
],
[
"C",
"n1"
],
[
"c3",
"c"
],
[
"N",
"3"
],
[
"N1",
"CC"
],
[
"C",
"c1n"
],
[
"cc",
"c"
],
[
"N",
"CC"
],
[
"C",
"N2"
],
[
"N1",
"CCN"
],
[
"c2",
"nc"
],
[
"c1",
"C"
],
[
"=",
"S"
],
[
"=",
"N"
],
[
"C",
"[C@@H]1"
],
[
"CO",
"c1cc"
],
[
"N",
"c1ccc"
],
[
"/C",
"=C"
],
[
"o",
"2"
],
[
"CCC",
"O"
],
[
"C",
"#"
],
[
"C[C@H]",
"1"
],
[
"C",
"c1ccccc1"
],
[
"cc",
"c2"
],
[
"s",
"2"
],
[
"[C@H]",
"3"
],
[
"[C@@H]",
"3"
],
[
"N2",
"CCC"
],
[
"C",
"c1cccc"
],
[
"c4",
"cccc"
],
[
"c1",
"cn"
],
[
"o",
"c"
],
[
"CC",
"NC"
],
[
"s",
"c"
],
[
"n",
"n"
],
[
"N2",
"C"
],
[
"-",
"c2ccc"
],
[
"C#",
"N"
],
[
"N2",
"CC"
],
[
"C",
"c1c"
],
[
"CC",
"S"
],
[
"CC",
"n1"
],
[
"C1",
"=O"
],
[
"C2",
"=O"
],
[
"cc1",
"C"
],
[
"[nH]",
"c"
],
[
"O=C",
"1"
],
[
"-",
"c2ccccc2"
],
[
"N",
"=C"
],
[
"C",
"c2ccccc2"
],
[
"c1",
"2"
],
[
"N2",
"CCN"
],
[
"CC",
"[C@H]"
],
[
"CC",
"[C@@H]"
],
[
"c4cccc",
"c4"
],
[
"C[C@H]",
"2"
],
[
"c1",
"=O"
],
[
"N",
"S"
],
[
"C",
"c1nc"
],
[
"c1cc",
"c2c"
],
[
"NC",
"1"
],
[
"CO",
"c1cccc"
],
[
"N",
"c2ccc"
],
[
"c3",
"n"
],
[
"c",
"n1"
],
[
"[nH]",
"1"
],
[
"C",
"="
],
[
"CO",
"c1ccccc1"
],
[
"c2ccccc2",
"1"
],
[
"c2",
"cn"
],
[
"N",
"[C@H]"
],
[
"N",
"[C@@H]"
],
[
"c1n",
"nc"
],
[
"c2",
"c1"
],
[
"CCO",
"c1ccc"
],
[
"S",
"CC"
],
[
"CCO",
"CC2"
],
[
"O",
"CO"
],
[
"c3",
"nc"
],
[
"c1n",
"cc"
],
[
"C",
"c2ccc"
],
[
"cc1",
"OC"
],
[
"NC",
"2"
],
[
"n",
"c3"
],
[
"CCCCC",
"2"
],
[
"C",
"=C"
],
[
"N1",
"CCO"
],
[
"n",
"n1"
],
[
"[C@]",
"1"
],
[
"CC",
"CC2"
],
[
"-",
"n2"
],
[
"c2n",
"cc"
],
[
"C",
"[C@@H]2"
],
[
"cc1",
"Cl"
],
[
"N",
"c1cccc"
],
[
"c2n",
"nc"
],
[
"[C@@]",
"1"
],
[
"CCCC",
"3"
],
[
"CCCCC",
"1"
],
[
"c2cc",
"c3c"
],
[
"-",
"c3ccccc3"
],
[
"n",
"n2"
],
[
"c4",
"ccc"
],
[
"CCC",
"2"
],
[
"n",
"o1"
],
[
"O",
"CCO"
],
[
"O",
"1"
],
[
"C",
"n2"
],
[
"S",
"C"
],
[
"-",
"c3ccc"
],
[
"N",
"c1cc"
],
[
"/C=C",
"/"
],
[
"Cn1",
"cc"
],
[
"N",
"[C@@H]1"
],
[
"c2",
"3"
],
[
"N",
"c1ccccc1"
],
[
"N",
"#"
],
[
"C",
"N1C"
],
[
"[C@@]",
"2"
],
[
"[C@]",
"2"
],
[
"C2",
"CC2"
],
[
"c2",
"C"
],
[
"o",
"3"
],
[
"N",
"CCC"
],
[
"N2",
"CCOCC2"
],
[
"N",
"[C@H]1"
]
]
}
}