{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": null, "pre_tokenizer": null, "post_processor": { "type": "TemplateProcessing", "single": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } } ], "pair": [ { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "A", "type_id": 0 } }, { "SpecialToken": { "id": "", "type_id": 0 } }, { "Sequence": { "id": "B", "type_id": 1 } }, { "SpecialToken": { "id": "", "type_id": 1 } } ], "special_tokens": { "": { "id": "", "ids": [ 1 ], "tokens": [ "" ] }, "": { "id": "", "ids": [ 2 ], "tokens": [ "" ] } } }, "decoder": { "type": "BPEDecoder", "suffix": "" }, "model": { "type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "vocab": { "": 0, "": 1, "": 2, "": 3, "": 4, "A": 5, "B": 6, "C": 7, "D": 8, "E": 9, "F": 10, "G": 11, "H": 12, "I": 13, "K": 14, "L": 15, "M": 16, "N": 17, "O": 18, "P": 19, "Q": 20, "R": 21, "S": 22, "T": 23, "U": 24, "V": 25, "W": 26, "X": 27, "Y": 28, "Z": 29, "AA": 30, "LL": 31, "SS": 32, "LA": 33, "LS": 34, "GG": 35, "LV": 36, "LR": 37, "LE": 38, "LG": 39, "LT": 40, "AV": 41, "AG": 42, "LP": 43, "LD": 44, "LI": 45, "AS": 46, "EE": 47, "RR": 48, "LK": 49, "VV": 50, "AT": 51, "AE": 52, "SG": 53, "DG": 54, "AR": 55, "KK": 56, "AI": 57, "AP": 58, "TT": 59, "LN": 60, "LF": 61, "LQ": 62, "AD": 63, "SV": 64, "ST": 65, "SI": 66, "SP": 67, "DE": 68, "TG": 69, "TV": 70, "SR": 71, "SE": 72, "DV": 73, "PP": 74, "KE": 75, "KI": 76, "DI": 77, "GV": 78, "AQ": 79, "AF": 80, "RV": 81, "TI": 82, "NI": 83, "PV": 84, "RE": 85, "SF": 86, "KV": 87, "NG": 88, "LY": 89, "RI": 90, "PG": 91, "RG": 92, "DD": 93, "PE": 94, "AK": 95, "NV": 96, "SD": 97, "TE": 98, "QQ": 99, "NE": 100, "SK": 101, "LH": 102, "SQ": 103, "GI": 104, "FV": 105, "TP": 106, "GE": 107, "SN": 108, "FI": 109, "AY": 110, "AN": 111, "QV": 112, "RK": 113, "SY": 114, "IV": 115, "FE": 116, "DP": 117, "RP": 118, "IE": 119, "QE": 120, "FG": 121, "LM": 122, "NN": 123, "KG": 124, "RT": 125, "RD": 126, "RQ": 127, "II": 128, "TD": 129, "AH": 130, "AM": 131, "YV": 132, "RF": 133, "EV": 134, "KN": 135, "KD": 136, "IG": 137, "LC": 138, "KT": 139, "KP": 140, "RY": 141, "SH": 142, "QG": 143, "NP": 144, "QI": 145, "FD": 146, "YG": 147, "RN": 148, "YE": 149, "TF": 150, "MV": 151, "RH": 152, "LW": 153, "QP": 154, "TN": 155, "DF": 156, "KQ": 157, "YI": 158, "ME": 159, "VE": 160, "LAA": 161, "PD": 162, "FF": 163, "PI": 164, "AC": 165, "ND": 166, "VG": 167, "TY": 168, "TQ": 169, "SM": 170, "AW": 171, "KY": 172, "HG": 173, "SC": 174, "HV": 175, "ID": 176, "KF": 177, "EG": 178, "KR": 179, "EI": 180, "MG": 181, "TR": 182, "NF": 183, "SW": 184, "TK": 185, "YD": 186, "NQ": 187, "ALL": 188, "MI": 189, "PT": 190, "NY": 191, "QD": 192, "GD": 193, "NT": 194, "HE": 195, "VI": 196, "PF": 197, "ALA": 198, "RS": 199 }, "merges": [ "A A", "L L", "S S", "L A", "L S", "G G", "L V", "L R", "L E", "L G", "L T", "A V", "A G", "L P", "L D", "L I", "A S", "E E", "R R", "L K", "V V", "A T", "A E", "S G", "D G", "A R", "K K", "A I", "A P", "T T", "L N", "L F", "L Q", "A D", "S V", "S T", "S I", "S P", "D E", "T G", "T V", "S R", "S E", "D V", "P P", "K E", "K I", "D I", "G V", "A Q", "A F", "R V", "T I", "N I", "P V", "R E", "S F", "K V", "N G", "L Y", "R I", "P G", "R G", "D D", "P E", "A K", "N V", "S D", "T E", "Q Q", "N E", "S K", "L H", "S Q", "G I", "F V", "T P", "G E", "S N", "F I", "A Y", "A N", "Q V", "R K", "S Y", "I V", "F E", "D P", "R P", "I E", "Q E", "F G", "L M", "N N", "K G", "R T", "R D", "R Q", "I I", "T D", "A H", "A M", "Y V", "R F", "E V", "K N", "K D", "I G", "L C", "K T", "K P", "R Y", "S H", "Q G", "N P", "Q I", "F D", "Y G", "R N", "Y E", "T F", "M V", "R H", "L W", "Q P", "T N", "D F", "K Q", "Y I", "M E", "V E", "L AA", "P D", "F F", "P I", "A C", "N D", "V G", "T Y", "T Q", "S M", "A W", "K Y", "H G", "S C", "H V", "I D", "K F", "E G", "K R", "E I", "M G", "T R", "N F", "S W", "T K", "Y D", "N Q", "A LL", "M I", "P T", "N Y", "Q D", "G D", "N T", "H E", "V I", "P F", "A LA", "R S" ] } }