| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "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": "[BOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[EOS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[MASK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 4, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": null, | |
| "pre_tokenizer": { | |
| "type": "Sequence", | |
| "pretokenizers": [ | |
| { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "\\[[^\\[\\]]+\\]|@TH|@AL|@SP|@TB|@OH|Cl|Br|se|as|\\-|\\#|\\$|\\\\|\\.|\\+|\\-|@@|\\(|\\)|\\*|He|Li|Be|Ne|Na|Mg|Al|Si|Cl|Ar|Ca|Ti|Cr|Mn|Fe|Ni|Cu|Zn|Ga|Ge|As|Se|Br|Kr|Rb|Sr|Zr|Mo|Tc|Ru|Rh|Pd|Ag|Cd|Te|Xe|Ba|La|Hf|Ta|Re|Ir|Pt|Au|Hg|Tl|Bi|At|Rn|Fr|Ra|Ac|Rf|Db|Sg|Bh|Mt|Ds|Rg|Nh|Fl|Mc|Lv|Ts|Og|Ce|Pr|Nd|Pm|Sm|Eu|Gd|Tb|Dy|Er|Tm|Lu|Th|Pa|Pu|Am|Cm|Bk|Cf|Es|Fm|Md|Lr|te|si|B|C|N|O|P|S|F|I|b|c|n|o|p|s|=|:|/|@|0|1|2|3|4|5|6|7|8|9|%|H|B|C|N|O|F|P|S|K|V|Y|I|W|U" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| }, | |
| { | |
| "type": "Split", | |
| "pattern": { | |
| "Regex": "@TH|@AL|@SP|@TB|@OH|He|Li|Be|Ne|Na|Mg|Al|Si|Cl|Ar|Ca|Sc|Ti|Cr|Mn|Fe|Co|Ni|Cu|Zn|Ga|Ge|As|Se|Br|Kr|Rb|Sr|Zr|Nb|Mo|Tc|Ru|Rh|Pd|Ag|Cd|In|Sn|Sb|Te|Xe|Cs|Ba|La|Hf|Ta|Re|Os|Ir|Pt|Au|Hg|Tl|Pb|Bi|Po|At|Rn|Fr|Ra|Ac|Rf|Db|Sg|Bh|Hs|Mt|Ds|Rg|Cn|Nh|Fl|Mc|Lv|Ts|Og|Ce|Pr|Nd|Pm|Sm|Eu|Gd|Tb|Dy|Ho|Er|Tm|Yb|Lu|Th|Pa|Np|Pu|Am|Cm|Bk|Cf|Es|Fm|Md|No|Lr|te|si|se|as|\\-|\\#|\\$|\\\\|\\.|\\+|\\-|@@|\\[|\\]|H|B|C|N|O|F|P|S|K|V|Y|I|W|U|b|c|n|o|p|s|=|:|/|@|0|1|2|3|4|5|6|7|8|9|%|%" | |
| }, | |
| "behavior": "Isolated", | |
| "invert": false | |
| } | |
| ] | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "[BOS]", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "[EOS]", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "[BOS]": { | |
| "id": "[BOS]", | |
| "ids": [ | |
| 1 | |
| ], | |
| "tokens": [ | |
| "[BOS]" | |
| ] | |
| }, | |
| "[EOS]": { | |
| "id": "[EOS]", | |
| "ids": [ | |
| 2 | |
| ], | |
| "tokens": [ | |
| "[EOS]" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": { | |
| "type": "WordPiece", | |
| "prefix": "", | |
| "cleanup": true | |
| }, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[PAD]": 0, | |
| "[BOS]": 1, | |
| "[EOS]": 2, | |
| "[MASK]": 3, | |
| "[UNK]": 4, | |
| "H": 5, | |
| "He": 6, | |
| "Li": 7, | |
| "Be": 8, | |
| "B": 9, | |
| "C": 10, | |
| "N": 11, | |
| "O": 12, | |
| "F": 13, | |
| "Ne": 14, | |
| "Na": 15, | |
| "Mg": 16, | |
| "Al": 17, | |
| "Si": 18, | |
| "P": 19, | |
| "S": 20, | |
| "Cl": 21, | |
| "Ar": 22, | |
| "K": 23, | |
| "Ca": 24, | |
| "Sc": 25, | |
| "Ti": 26, | |
| "V": 27, | |
| "Cr": 28, | |
| "Mn": 29, | |
| "Fe": 30, | |
| "Co": 31, | |
| "Ni": 32, | |
| "Cu": 33, | |
| "Zn": 34, | |
| "Ga": 35, | |
| "Ge": 36, | |
| "As": 37, | |
| "Se": 38, | |
| "Br": 39, | |
| "Kr": 40, | |
| "Rb": 41, | |
| "Sr": 42, | |
| "Y": 43, | |
| "Zr": 44, | |
| "Nb": 45, | |
| "Mo": 46, | |
| "Tc": 47, | |
| "Ru": 48, | |
| "Rh": 49, | |
| "Pd": 50, | |
| "Ag": 51, | |
| "Cd": 52, | |
| "In": 53, | |
| "Sn": 54, | |
| "Sb": 55, | |
| "Te": 56, | |
| "I": 57, | |
| "Xe": 58, | |
| "Cs": 59, | |
| "Ba": 60, | |
| "La": 61, | |
| "Hf": 62, | |
| "Ta": 63, | |
| "W": 64, | |
| "Re": 65, | |
| "Os": 66, | |
| "Ir": 67, | |
| "Pt": 68, | |
| "Au": 69, | |
| "Hg": 70, | |
| "Tl": 71, | |
| "Pb": 72, | |
| "Bi": 73, | |
| "Po": 74, | |
| "At": 75, | |
| "Rn": 76, | |
| "Fr": 77, | |
| "Ra": 78, | |
| "Ac": 79, | |
| "Rf": 80, | |
| "Db": 81, | |
| "Sg": 82, | |
| "Bh": 83, | |
| "Hs": 84, | |
| "Mt": 85, | |
| "Ds": 86, | |
| "Rg": 87, | |
| "Cn": 88, | |
| "Nh": 89, | |
| "Fl": 90, | |
| "Mc": 91, | |
| "Lv": 92, | |
| "Ts": 93, | |
| "Og": 94, | |
| "Ce": 95, | |
| "Pr": 96, | |
| "Nd": 97, | |
| "Pm": 98, | |
| "Sm": 99, | |
| "Eu": 100, | |
| "Gd": 101, | |
| "Tb": 102, | |
| "Dy": 103, | |
| "Ho": 104, | |
| "Er": 105, | |
| "Tm": 106, | |
| "Yb": 107, | |
| "Lu": 108, | |
| "Th": 109, | |
| "Pa": 110, | |
| "U": 111, | |
| "Np": 112, | |
| "Pu": 113, | |
| "Am": 114, | |
| "Cm": 115, | |
| "Bk": 116, | |
| "Cf": 117, | |
| "Es": 118, | |
| "Fm": 119, | |
| "Md": 120, | |
| "No": 121, | |
| "Lr": 122, | |
| "te": 123, | |
| "si": 124, | |
| "b": 125, | |
| "c": 126, | |
| "n": 127, | |
| "o": 128, | |
| "p": 129, | |
| "s": 130, | |
| "se": 131, | |
| "as": 132, | |
| "-": 133, | |
| "=": 134, | |
| "#": 135, | |
| "$": 136, | |
| ":": 137, | |
| "/": 138, | |
| "\\": 139, | |
| ".": 140, | |
| "+": 141, | |
| "@": 142, | |
| "@@": 143, | |
| "@TH": 144, | |
| "@AL": 145, | |
| "@SP": 146, | |
| "@TB": 147, | |
| "@OH": 148, | |
| "(": 149, | |
| ")": 150, | |
| "*": 151, | |
| "0": 152, | |
| "1": 153, | |
| "2": 154, | |
| "3": 155, | |
| "4": 156, | |
| "5": 157, | |
| "6": 158, | |
| "7": 159, | |
| "8": 160, | |
| "9": 161, | |
| "%": 162, | |
| "[": 163, | |
| "]": 164 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |