Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,550 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "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": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "(\\[[^\\]]+]|C\\(=N\\)N|CCC\\(C\\)|\\(CCCN\\)|NC\\(=O\\)|C\\(C\\)=O|=C\\(N\\)N|N=C\\(N\\)|NC\\(=N\\)|C\\(=O\\)C|CS\\(=O\\)|OC\\(=O\\)|C\\(=O\\)c|c\\(=O\\)n|C\\(=O\\)O|C\\(N\\)=O|cc\\(Br\\)|CC\\(=O\\)|C\\(=O\\)N|ccc\\(C\\)|ccc\\(F\\)|c\\(=O\\)|C\\(=N\\)|c\\(O\\)c|NC\\(C\\)|n\\(C\\)c|CC\\(O\\)|cc\\(N\\)|CC\\(C\\)|cc\\(C\\)|C\\(=O\\)|cc\\(O\\)|c\\(N\\)c|c\\(Cl\\)|C\\(N\\)N|N\\(C\\)C|NC\\(N\\)|=C\\(N\\)|C\\(O\\)C|c\\(OC\\)|\\(C#N\\)|C\\(C\\)C|CC\\(N\\)|C\\(C\\)N|c\\(CO\\)|c\\(Br\\)|\\(CCO\\)|C\\(CC\\)|S\\(=O\\)|c\\(C\\)c|\\(=N\\)|c\\(O\\)|\\(Br\\)|\\(CS\\)|c\\(C\\)|\\(CC\\)|c\\(I\\)|C\\(C\\)|N\\(C\\)|C\\(O\\)|C\\(I\\)|C\\(F\\)|\\(Cl\\)|n\\(C\\)|\\(OC\\)|\\(=O\\)|c\\(F\\)|CCCN\\)|\\(=S\\)|c\\(N\\)|\\(CO\\)|C\\(N\\)|\\(C\\)|ccccc|\\(S\\)|\\(F\\)|\\(O\\)|C#N\\)|CCO\\)|\\(N\\)|C\\(=N|\\(I\\)|CSSC|=N\\)|CC=O|CCCO|Cl\\)|CCNO|=O\\)|CCSC|\\(=N|CO\\)|CCNC|CCCC|=S\\)|CN=C|CCCS|cccc|CCCN|Br\\)|cccn|CS\\)|C=CC|OC\\)|CC=C|cnn|=NC|COC|OCC|\\(O|CCS|CNc|#Cc|=CC|ccn|C=C|CSc|ccc|NCc|CCO|N=C|cnc|I\\)|CCc|OCc|CCl|ccs|COc|CCn|CSC|SCC|NCC|CCN|CNC|C#C|C=O|CNO|CCC|SSC|C#N|O=C|NOC|S\\)|csc|ncc|C\\)|N\\)|\\(C|ncn|F\\)|O\\)|N#C|nnc|CSS|cco|Cl|NC|nc|co|CS|CO|no|cc|CN|cn|SS|OC|\\)|SN|nn|CC|#C|NO|=S|NS|cs|=C|Oc|=O|oc|Nc|Cc|=N|NN|C=|C#|\\(|SC|sc|Br|N#|#N|p|O|I|N|C|s|=|c|B|S|F|n|P|#|o)"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[SEP]": {
+        "id": "[SEP]",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "[SEP]"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[SEP]": 3,
+      "[MASK]": 4,
+      ":": 5,
+      "%11": 6,
+      "-": 7,
+      "[As]": 8,
+      "[pH]": 9,
+      "[Po]": 10,
+      "[Ra]": 11,
+      "[3H]": 12,
+      "[S-]": 13,
+      "8": 14,
+      "%21": 15,
+      "[CH-]": 16,
+      "[IH]": 17,
+      "P": 18,
+      "[SeH]": 19,
+      "[O]": 20,
+      "4": 21,
+      "/": 22,
+      "[N-]": 23,
+      "[129Xe]": 24,
+      "[Cl+3]": 25,
+      "3": 26,
+      "[C@@]": 27,
+      "[11CH3]": 28,
+      "[13C]": 29,
+      "[Sn+]": 30,
+      "[P@@]": 31,
+      "[Ge]": 32,
+      "[BH3-]": 33,
+      "[123I]": 34,
+      "[14CH2]": 35,
+      "[Al-]": 36,
+      "[Si]": 37,
+      "[S@]": 38,
+      "[W]": 39,
+      "=": 40,
+      "%19": 41,
+      "Cl": 42,
+      "[Cl+2]": 43,
+      "%14": 44,
+      "[Al]": 45,
+      "9": 46,
+      "[B-]": 47,
+      "[Cl+]": 48,
+      "[TlH2]": 49,
+      "[NH2+]": 50,
+      "[11CH]": 51,
+      "[SnH]": 52,
+      "[SiH3]": 53,
+      "[Sn]": 54,
+      "[11C]": 55,
+      "S": 56,
+      "[SiH2]": 57,
+      "%18": 58,
+      "[BH-]": 59,
+      "[Ru]": 60,
+      "%10": 61,
+      "[V]": 62,
+      "[o+]": 63,
+      "[O+]": 64,
+      "c": 65,
+      "[I-]": 66,
+      "[C@@H]": 67,
+      "n": 68,
+      "2": 69,
+      "[Se-]": 70,
+      "[N+]": 71,
+      "N": 72,
+      "s": 73,
+      "[PH+]": 74,
+      "[C@]": 75,
+      "[N@]": 76,
+      "[C+]": 77,
+      "[s+]": 78,
+      "[N@+]": 79,
+      "[125I]": 80,
+      "[cH-]": 81,
+      "[Th]": 82,
+      "C": 83,
+      "[Sb]": 84,
+      "5": 85,
+      "[c-]": 86,
+      "#": 87,
+      "[Ca]": 88,
+      "%16": 89,
+      "[Tl]": 90,
+      "[18F]": 91,
+      "[223Ra]": 92,
+      "[BH2-]": 93,
+      "[O-]": 94,
+      "[Bi]": 95,
+      "[te]": 96,
+      "Br": 97,
+      "[Cr]": 98,
+      "[N@@]": 99,
+      "[Hg]": 100,
+      "[S@+]": 101,
+      "\\": 102,
+      "[n+]": 103,
+      "%15": 104,
+      "[123Te]": 105,
+      "[C-]": 106,
+      "1": 107,
+      "[NH+]": 108,
+      "[I+]": 109,
+      "[CH]": 110,
+      "%13": 111,
+      "[Pb]": 112,
+      "[14C]": 113,
+      "[2H]": 114,
+      "[P@]": 115,
+      "[OH+]": 116,
+      ")": 117,
+      "[Tc]": 118,
+      "[se+]": 119,
+      "[NH-]": 120,
+      "[nH]": 121,
+      "B": 122,
+      "[CH2]": 123,
+      "[P+]": 124,
+      "[se]": 125,
+      "[In]": 126,
+      "[Te]": 127,
+      "[Se+]": 128,
+      "%12": 129,
+      "[S+]": 130,
+      "o": 131,
+      "[C]": 132,
+      "[N@@+]": 133,
+      "[n-]": 134,
+      "6": 135,
+      "[S@@]": 136,
+      "[nH+]": 137,
+      "[Si+]": 138,
+      "[PH]": 139,
+      "[Hg+]": 140,
+      "[C@H]": 141,
+      "[Ga]": 142,
+      "[S@@+]": 143,
+      "[NH3+]": 144,
+      "[SiH]": 145,
+      "[11c]": 146,
+      "%20": 147,
+      "%17": 148,
+      "(": 149,
+      "O": 150,
+      "[IH2]": 151,
+      "[As+]": 152,
+      "F": 153,
+      "[CH2-]": 154,
+      "[Se]": 155,
+      "[c+]": 156,
+      "%23": 157,
+      "[SH]": 158,
+      "I": 159,
+      "7": 160,
+      "%22": 161,
+      "[Os]": 162,
+      "[OH]": 163,
+      "p": 164,
+      "[P@+]": 165,
+      "[Ag+]": 166,
+      "[Ag-4]": 167,
+      "[Ag]": 168,
+      "[Al-3]": 169,
+      "[AsH3]": 170,
+      "[AsH]": 171,
+      "[At]": 172,
+      "[B@-]": 173,
+      "[B@@-]": 174,
+      "[B]": 175,
+      "[Ba]": 176,
+      "[Br+2]": 177,
+      "[BrH]": 178,
+      "[Br]": 179,
+      "[CH3]": 180,
+      "[CaH2]": 181,
+      "[Cs]": 182,
+      "[FH]": 183,
+      "[F]": 184,
+      "[H]": 185,
+      "[He]": 186,
+      "[I+2]": 187,
+      "[I+3]": 188,
+      "[I]": 189,
+      "[K]": 190,
+      "[Kr]": 191,
+      "[Li+]": 192,
+      "[LiH]": 193,
+      "[MgH2]": 194,
+      "[Mg]": 195,
+      "[NH3]": 196,
+      "[N]": 197,
+      "[Na]": 198,
+      "[OH2]": 199,
+      "[P@@+]": 200,
+      "[PH2]": 201,
+      "[P]": 202,
+      "[Rb]": 203,
+      "[SH+]": 204,
+      "[SH2]": 205,
+      "[S]": 206,
+      "[Se-2]": 207,
+      "[SeH2]": 208,
+      "[Si@]": 209,
+      "[SrH2]": 210,
+      "[TeH]": 211,
+      "[Xe]": 212,
+      "[Zn+2]": 213,
+      "[Zn-2]": 214,
+      "[Zn]": 215,
+      "[n]": 216,
+      "[te+]": 217,
+      "=O": 218,
+      "CC": 219,
+      "NC": 220,
+      "CO": 221,
+      "cc": 222,
+      "CCC": 223,
+      "CCCC": 224,
+      "ccc": 225,
+      "CCN": 226,
+      "CCCN": 227,
+      "CN": 228,
+      "CNC": 229,
+      "cccc": 230,
+      "ccccc": 231,
+      "N)": 232,
+      "(N)": 233,
+      "=O)": 234,
+      "(=O)": 235,
+      "C(=O)": 236,
+      "C(=O)N": 237,
+      "O)": 238,
+      "(C": 239,
+      "(C)": 240,
+      "C(C)": 241,
+      "C(C)C": 242,
+      "CC(=O)": 243,
+      "C(=O)O": 244,
+      "C(=O)C": 245,
+      "C(N)": 246,
+      "CC(N)": 247,
+      "C(N)=O": 248,
+      "CO)": 249,
+      "(CO)": 250,
+      "CC(C)": 251,
+      "CS": 252,
+      "=N": 253,
+      "CCNC": 254,
+      "NC(=O)": 255,
+      "=N)": 256,
+      "(=N)": 257,
+      "C(=N)": 258,
+      "CC=O": 259,
+      "CCCN)": 260,
+      "(CCCN)": 261,
+      "NC(=N)": 262,
+      "Br)": 263,
+      "(Br)": 264,
+      "F)": 265,
+      "(F)": 266,
+      "S)": 267,
+      "(S)": 268,
+      "C)": 269,
+      "(O)": 270,
+      "CCS": 271,
+      "CCCS": 272,
+      "CCSC": 273,
+      "cn": 274,
+      "ccn": 275,
+      "cccn": 276,
+      "CSC": 277,
+      "=C": 278,
+      "CCO": 279,
+      "(O": 280,
+      "(=N": 281,
+      "C(=N": 282,
+      "c(O)": 283,
+      "OC": 284,
+      "SCC": 285,
+      "ccc(F)": 286,
+      "S(=O)": 287,
+      "O=C": 288,
+      "CCc": 289,
+      "OC(=O)": 290,
+      "C#": 291,
+      "Cc": 292,
+      "C=C": 293,
+      "C=": 294,
+      "#N": 295,
+      "C#N": 296,
+      "ccs": 297,
+      "NO": 298,
+      "C(O)": 299,
+      "csc": 300,
+      "ccc(C)": 301,
+      "cc(Br)": 302,
+      "ncn": 303,
+      "CCNO": 304,
+      "CCCO": 305,
+      "CSS": 306,
+      "CSSC": 307,
+      "=CC": 308,
+      "I)": 309,
+      "(I)": 310,
+      "CNO": 311,
+      "N(C)": 312,
+      "N(C)C": 313,
+      "C(N)N": 314,
+      "NOC": 315,
+      "C(C)=O": 316,
+      "#C": 317,
+      "cco": 318,
+      "NS": 319,
+      "SN": 320,
+      "c(=O)n": 321,
+      "=S)": 322,
+      "(=S)": 323,
+      "c(N)c": 324,
+      "N=C": 325,
+      "SC": 326,
+      "SSC": 327,
+      "CCC(C)": 328,
+      "c(=O)": 329,
+      "C#N)": 330,
+      "(C#N)": 331,
+      "SS": 332,
+      "=S": 333,
+      "oc": 334,
+      "co": 335,
+      "no": 336,
+      "N#": 337,
+      "N#C": 338,
+      "nc": 339,
+      "sc": 340,
+      "C(=N)N": 341,
+      "C=O": 342,
+      "c(F)": 343,
+      "C(F)": 344,
+      "c(I)": 345,
+      "C(I)": 346,
+      "cnn": 347,
+      "cc(N)": 348,
+      "NC(N)": 349,
+      "OC)": 350,
+      "(OC)": 351,
+      "c(OC)": 352,
+      "c(Br)": 353,
+      "c(N)": 354,
+      "cc(O)": 355,
+      "CS)": 356,
+      "(CS)": 357,
+      "Oc": 358,
+      "cnc": 359,
+      "Cl)": 360,
+      "(Cl)": 361,
+      "c(Cl)": 362,
+      "c(O)c": 363,
+      "NCC": 364,
+      "COC": 365,
+      "OCC": 366,
+      "Nc": 367,
+      "ncc": 368,
+      "cc(C)": 369,
+      "nn": 370,
+      "cs": 371,
+      "c(C)c": 372,
+      "COc": 373,
+      "C(=O)c": 374,
+      "c(C)": 375,
+      "(CC)": 376,
+      "NCc": 377,
+      "nnc": 378,
+      "C(O)C": 379,
+      "=C(N)": 380,
+      "C=CC": 381,
+      "=C(N)N": 382,
+      "N=C(N)": 383,
+      "OCc": 384,
+      "CC=C": 385,
+      "CCl": 386,
+      "CCn": 387,
+      "CNc": 388,
+      "CC(O)": 389,
+      "NN": 390,
+      "CSc": 391,
+      "NC(C)": 392,
+      "CS(=O)": 393,
+      "C(CC)": 394,
+      "C#C": 395,
+      "C(C)N": 396,
+      "CCO)": 397,
+      "(CCO)": 398,
+      "CN=C": 399,
+      "n(C)": 400,
+      "n(C)c": 401,
+      "c(CO)": 402,
+      "#Cc": 403,
+      "=NC": 404
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 768,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}