{ "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 } ], "normalizer": null, "pre_tokenizer": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "post_processor": null, "decoder": { "type": "ByteLevel", "add_prefix_space": true, "trim_offsets": true, "use_regex": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "", "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, "²": 6, "³": 7, "´": 8, "µ": 9, "¶": 10, "·": 11, "¸": 12, "¹": 13, "º": 14, "»": 15, "¼": 16, "½": 17, "¾": 18, "Ð": 19, "Ñ": 20, "Ġ": 21, "Ģ": 22, "ģ": 23, "Ĥ": 24, "ĥ": 25, "Ħ": 26, "Ĩ": 27, "ĩ": 28, "ĭ": 29, "Į": 30, "ı": 31, "ij": 32, "н": 33, "нÐ": 34, "й": 35, "ĠÑ": 36, "ÑĢ": 37, "о": 38, "ĠнÐ": 39, "Ġна": 40, "ÑĢÐ": 41, "Ñĭ": 42, "Ñĭй": 43, "Ñģ": 44, "ĠÐ": 45, "е": 46, "Ñĥ": 47, "ĠÑĦ": 48, "л": 49, "¸Ñģ": 50, "не": 51, "оне": 52, "ĠнаÑĢÐ": 53, "Ñĥй": 54, "ĠÑĦоне": 55, "¸ÑģÑĥй": 56, "ĠнаÑĢиÑģÑĥй": 57, "ĠÑģ": 58, "в": 59, "нÑĭй": 60, "ÑĤ": 61, "Ġк": 62, "Ñij": 63, "и": 64, "ни": 65, "ÑĢа": 66, "а": 67, "ĠÑĤ": 68, "Ġз": 69, "ел": 70, "ĠÑģе": 71, "ини": 72, "ол": 73, "ов": 74, "ÑĥÐ": 75, "м": 76, "ÑĢÑĭй": 77, "ÑģнÑĭй": 78, "еÑĤ": 79, "ĠÑģини": 80, "ĠкÑĢа": 81, "ÑijнÑĭй": 82, "Ġзел": 83, "ĠÑģеÑĢÑĭй": 84, "ĠÑģиний": 85, "ĠкÑĢаÑģнÑĭй": 86, "ĠзелÑijнÑĭй": 87, "³Ð¾Ð»": 88, "д": 89, "з": 90, "к": 91, "Ģо": 92, "ĠÑĢо": 93, "ÑĢе": 94, "овÑĭй": 95, "лÑĭй": 96, "ĠÑģв": 97, "Ñijм": 98, "ĠÑĤÑijм": 99, "еÑĤлÑĭй": 100, "ĠÑģвеÑĤлÑĭй": 101, "ĠÑĤÑijмнÑĭй": 102, "±Ð¾": 103, "±ÐµÐ»": 104, "´Ñ": 105, "¶Ðµ": 106, "¶Ñij": 107, "»Ð¸Ð½Ð¸": 108, "б": 109, "Ñĩ": 110, "ÑĮ": 111, "Ñı": 112, "Ġо": 113, "Ġов": 114, "Ĩе": 115, "нже": 116, "ÑĢÑĥÐ": 117, "оÑĩ": 118, "ÑĢдÑ": 119, "ÑģÑĤ": 120, "Ġгол": 121, "Ġбел": 122, "ĠжÑij": 123, "Ġлини": 124, "ез": 125, "ĠÑĦи": 126, "лÑĤ": 127, "вÑĭй": 128, "ва": 129, "вез": 130, "ĠкÑĢе": 131, "ĠкÑĢÑĥÐ": 132, "Ġква": 133, "ник": 134, "ÑĢаÑĤ": 135, "ÑĢанже": 136, "ал": 137, "ĠÑĤÑĢе": 138, "ĠÑĤоÑĩ": 139, "Ġзвез": 140, "ĠÑģеÑĢдÑ": 141, "олеÑĤ": 142, "Ñĥгол": 143, "Ñĥбо": 144, "мб": 145, "да": 146, "дÑĢаÑĤ": 147, "зовÑĭй": 148, "ка": 149, "ĠÑĢомб": 150, "ĠÑĢозовÑĭй": 151, "ÑĮник": 152, "ĠоÑĢанже": 153, "Ġовал": 154, "ĠголÑĥбо": 155, "ĠбелÑĭй": 156, "ĠжÑijлÑĤ": 157, "ĠлиниÑı": 158, "ĠÑĦиолеÑĤ": 159, "ĠкÑĢеÑģÑĤ": 160, "ĠкÑĢÑĥг": 161, "ĠквадÑĢаÑĤ": 162, "ĠÑĤÑĢеÑĥгол": 163, "ĠÑĤоÑĩка": 164, "Ġзвезда": 165, "ĠÑģеÑĢдÑĨе": 166, "ĠоÑĢанжевÑĭй": 167, "ĠголÑĥбой": 168, "ĠжÑijлÑĤÑĭй": 169, "ĠÑĦиолеÑĤовÑĭй": 170, "ĠÑĤÑĢеÑĥголÑĮник": 171 }, "merges": [ [ "Ð", "½" ], [ "н", "Ð" ], [ "Ð", "¹" ], [ "Ġ", "Ñ" ], [ "Ñ", "Ģ" ], [ "Ð", "¾" ], [ "Ġ", "нÐ" ], [ "ĠнÐ", "°" ], [ "ÑĢ", "Ð" ], [ "Ñ", "ĭ" ], [ "Ñĭ", "й" ], [ "Ñ", "ģ" ], [ "Ġ", "Ð" ], [ "Ð", "µ" ], [ "Ñ", "ĥ" ], [ "ĠÑ", "Ħ" ], [ "Ð", "»" ], [ "¸", "Ñģ" ], [ "нÐ", "µ" ], [ "о", "не" ], [ "Ġна", "ÑĢÐ" ], [ "Ñĥ", "й" ], [ "ĠÑĦ", "оне" ], [ "¸Ñģ", "Ñĥй" ], [ "ĠнаÑĢÐ", "¸ÑģÑĥй" ], [ "ĠÑ", "ģ" ], [ "Ð", "²" ], [ "н", "Ñĭй" ], [ "Ñ", "Ĥ" ], [ "ĠÐ", "º" ], [ "Ñ", "ij" ], [ "Ð", "¸" ], [ "нÐ", "¸" ], [ "ÑĢÐ", "°" ], [ "Ð", "°" ], [ "ĠÑ", "Ĥ" ], [ "ĠÐ", "·" ], [ "е", "л" ], [ "ĠÑģ", "е" ], [ "и", "ни" ], [ "о", "л" ], [ "о", "в" ], [ "Ñĥ", "Ð" ], [ "Ð", "¼" ], [ "ÑĢ", "Ñĭй" ], [ "Ñģ", "нÑĭй" ], [ "е", "ÑĤ" ], [ "ĠÑģ", "ини" ], [ "Ġк", "ÑĢа" ], [ "Ñij", "нÑĭй" ], [ "Ġз", "ел" ], [ "ĠÑģе", "ÑĢÑĭй" ], [ "ĠÑģини", "й" ], [ "ĠкÑĢа", "ÑģнÑĭй" ], [ "Ġзел", "ÑijнÑĭй" ], [ "³", "ол" ], [ "Ð", "´" ], [ "Ð", "·" ], [ "Ð", "º" ], [ "Ģ", "о" ], [ "ĠÑ", "Ģо" ], [ "ÑĢÐ", "µ" ], [ "ов", "Ñĭй" ], [ "л", "Ñĭй" ], [ "ĠÑģ", "в" ], [ "Ñij", "м" ], [ "ĠÑĤ", "Ñijм" ], [ "еÑĤ", "лÑĭй" ], [ "ĠÑģв", "еÑĤлÑĭй" ], [ "ĠÑĤÑijм", "нÑĭй" ], [ "±", "о" ], [ "±", "ел" ], [ "´", "Ñ" ], [ "¶", "е" ], [ "¶", "Ñij" ], [ "»", "ини" ], [ "Ð", "±" ], [ "Ñ", "ĩ" ], [ "Ñ", "Į" ], [ "Ñ", "ı" ], [ "Ġ", "о" ], [ "Ġ", "ов" ], [ "Ĩ", "е" ], [ "нÐ", "¶Ðµ" ], [ "ÑĢ", "ÑĥÐ" ], [ "о", "Ñĩ" ], [ "ÑĢÐ", "´Ñ" ], [ "Ñģ", "ÑĤ" ], [ "ĠÐ", "³Ð¾Ð»" ], [ "ĠÐ", "±ÐµÐ»" ], [ "ĠÐ", "¶Ñij" ], [ "ĠÐ", "»Ð¸Ð½Ð¸" ], [ "е", "з" ], [ "ĠÑĦ", "и" ], [ "л", "ÑĤ" ], [ "в", "Ñĭй" ], [ "в", "а" ], [ "в", "ез" ], [ "Ġк", "ÑĢе" ], [ "Ġк", "ÑĢÑĥÐ" ], [ "Ġк", "ва" ], [ "ни", "к" ], [ "ÑĢа", "ÑĤ" ], [ "ÑĢа", "нже" ], [ "а", "л" ], [ "ĠÑĤ", "ÑĢе" ], [ "ĠÑĤ", "оÑĩ" ], [ "Ġз", "вез" ], [ "ĠÑģе", "ÑĢдÑ" ], [ "ол", "еÑĤ" ], [ "ÑĥÐ", "³Ð¾Ð»" ], [ "ÑĥÐ", "±Ð¾" ], [ "м", "б" ], [ "д", "а" ], [ "д", "ÑĢаÑĤ" ], [ "з", "овÑĭй" ], [ "к", "а" ], [ "ĠÑĢо", "мб" ], [ "ĠÑĢо", "зовÑĭй" ], [ "ÑĮ", "ник" ], [ "Ġо", "ÑĢанже" ], [ "Ġов", "ал" ], [ "Ġгол", "Ñĥбо" ], [ "Ġбел", "Ñĭй" ], [ "ĠжÑij", "лÑĤ" ], [ "Ġлини", "Ñı" ], [ "ĠÑĦи", "олеÑĤ" ], [ "ĠкÑĢе", "ÑģÑĤ" ], [ "ĠкÑĢÑĥÐ", "³" ], [ "Ġква", "дÑĢаÑĤ" ], [ "ĠÑĤÑĢе", "Ñĥгол" ], [ "ĠÑĤоÑĩ", "ка" ], [ "Ġзвез", "да" ], [ "ĠÑģеÑĢдÑ", "Ĩе" ], [ "ĠоÑĢанже", "вÑĭй" ], [ "ĠголÑĥбо", "й" ], [ "ĠжÑijлÑĤ", "Ñĭй" ], [ "ĠÑĦиолеÑĤ", "овÑĭй" ], [ "ĠÑĤÑĢеÑĥгол", "ÑĮник" ] ] } }