{ "added_tokens_decoder": { "0": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "1": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "2": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "3": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "4": { "content": "a", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "486": { "content": "8", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "1338": { "content": "R", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "1476": { "content": "ı", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "1601": { "content": "U", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "1681": { "content": "[", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "2586": { "content": ":", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "2664": { "content": "–", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "3200": { "content": "9", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "3890": { "content": "Ú", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "4573": { "content": "Í", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "5051": { "content": "e", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "5770": { "content": "&", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "5798": { "content": "ę", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "6522": { "content": "h", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "6967": { "content": "·", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "7456": { "content": "i", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "7690": { "content": "(", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "8053": { "content": "+", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "9026": { "content": "=", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "9170": { "content": "J", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "9745": { "content": "l", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "10719": { "content": "α", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "10960": { "content": "W", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "11317": { "content": "ι", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "11938": { "content": ")", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "12162": { "content": "Z", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "12816": { "content": "X", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "14022": { "content": "ν", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "14301": { "content": "<", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "14898": { "content": "*", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "15811": { "content": "z", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "15994": { "content": "j", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "16191": { "content": "t", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "16648": { "content": "Y", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "17367": { "content": "g", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "17521": { "content": "×", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "17725": { "content": "•", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "18215": { "content": "n", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "19064": { "content": "ɔ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "20642": { "content": "・", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "20825": { "content": "è", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "27134": { "content": "~", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "28019": { "content": "c", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "28268": { "content": "0", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "28431": { "content": "'", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "30252": { "content": "—", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "30424": { "content": "✓", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "30955": { "content": "ਔ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "31285": { "content": "ˌ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "32650": { "content": "{", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "33855": { "content": "’", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "33917": { "content": "Ā", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "33968": { "content": "p", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "34490": { "content": "]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "34779": { "content": "Q", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "34796": { "content": "b", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35059": { "content": "א", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35161": { "content": "A", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35354": { "content": "π", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35544": { "content": "S", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35815": { "content": ",", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35816": { "content": "o", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "35934": { "content": "2", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "36209": { "content": "?", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "36967": { "content": "u", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "37093": { "content": "v", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "38167": { "content": "3", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "38459": { "content": "!", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "38460": { "content": "‘", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "38844": { "content": "m", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "39379": { "content": "%", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "39415": { "content": "D", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "39539": { "content": ".", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "39563": { "content": "τ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "39905": { "content": "r", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40217": { "content": "\\", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40227": { "content": "f", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40392": { "content": "x", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40582": { "content": "í", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40705": { "content": "w", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40831": { "content": "$", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "40956": { "content": "C", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "41403": { "content": "_", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "42309": { "content": "γ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "43154": { "content": "ה", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "43634": { "content": "y", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "45105": { "content": "I", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "45201": { "content": "\"", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "45202": { "content": "B", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "45785": { "content": "|", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "45964": { "content": "M", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46192": { "content": "s", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46318": { "content": "K", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46500": { "content": "み", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46502": { "content": "ṇ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46579": { "content": "ṭ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46702": { "content": "4", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "46735": { "content": "T", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "47106": { "content": "/", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "47597": { "content": "E", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "47992": { "content": "Á", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "48318": { "content": "O", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "48693": { "content": "P", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "49224": { "content": "d", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "49458": { "content": "á", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "49933": { "content": "G", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "49945": { "content": "°", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50155": { "content": ";", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "50934": { "content": "5", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "52165": { "content": "-", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "52613": { "content": "}", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53031": { "content": "÷", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53233": { "content": "N", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53278": { "content": "H", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53504": { "content": "ṛ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53669": { "content": "V", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53904": { "content": "q", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "53958": { "content": "L", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "54359": { "content": "и", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "55144": { "content": "6", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "55175": { "content": "k", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "55410": { "content": "F", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "56620": { "content": "7", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "56739": { "content": "ú", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57521": { "content": "", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true }, "57522": { "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57523": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "57524": { "content": "", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }, "57525": { "content": "ਥ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57526": { "content": "ੱ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57527": { "content": "્", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57528": { "content": "ਯ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57529": { "content": "ਲ਼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57530": { "content": "॥", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57531": { "content": "च", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57532": { "content": "Ṇ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57533": { "content": "ਐ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57534": { "content": "ि", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57535": { "content": "અ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57536": { "content": "ਦ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57537": { "content": "Ī", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57538": { "content": "ॉ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57539": { "content": "ा", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57540": { "content": "ਅ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57541": { "content": "ਚ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57542": { "content": "घ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57543": { "content": "ਞ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57544": { "content": "ਂ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57545": { "content": "ਟ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57546": { "content": "ੈ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57547": { "content": "य", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57548": { "content": "ਧ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57549": { "content": "ો", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57550": { "content": "ਊ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57551": { "content": "ॅ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57552": { "content": "ˈ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57553": { "content": "भ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57554": { "content": "ਿ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57555": { "content": "ज", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57556": { "content": "ل", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57557": { "content": "न", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57558": { "content": "ਆ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57559": { "content": "ਗ਼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57560": { "content": "ਰ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57561": { "content": "੍", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57562": { "content": "ય", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57563": { "content": "्", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57564": { "content": "ਛ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57565": { "content": "ਡ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57566": { "content": "र", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57567": { "content": "थ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57568": { "content": "ੁ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57569": { "content": "³", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57570": { "content": "י", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57571": { "content": "ੲ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57572": { "content": "म", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57573": { "content": "Ḥ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57574": { "content": "ਤ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57575": { "content": "ગ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57576": { "content": "ਜ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57577": { "content": "ੰ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57578": { "content": "ै", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57579": { "content": "ਣ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57580": { "content": "ਬ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57581": { "content": "व", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57582": { "content": "د", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57583": { "content": "т", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57584": { "content": "ી", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57585": { "content": "ਪ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57586": { "content": "…", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57587": { "content": "½", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57588": { "content": "²", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57589": { "content": "ग", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57590": { "content": "ד", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57591": { "content": "उ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57592": { "content": "ઘ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57593": { "content": "ੇ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57594": { "content": "ੋ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57595": { "content": "Ṉ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57596": { "content": "ठ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57597": { "content": "ल", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57598": { "content": "ਜ਼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57599": { "content": "ड", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57600": { "content": "ṉ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57601": { "content": "ਫ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57602": { "content": "ਮ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57603": { "content": "ਸ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57604": { "content": "੫", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57605": { "content": "ਵ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57606": { "content": "त", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57607": { "content": "¼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57608": { "content": "ਉ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57609": { "content": "¶", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57610": { "content": "Ι", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57611": { "content": "р", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57612": { "content": "ਕ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57613": { "content": "ो", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57614": { "content": "ਾ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57615": { "content": "છ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57616": { "content": "о", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57617": { "content": "સ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57618": { "content": "ਘ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57619": { "content": "¹", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57620": { "content": "द", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57621": { "content": "ḍ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57622": { "content": "ष", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57623": { "content": "ੜ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57624": { "content": "प", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57625": { "content": "ਭ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57626": { "content": "Ṛ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57627": { "content": "ੳ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57628": { "content": "ત", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57629": { "content": "ર", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57630": { "content": "Ṭ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57631": { "content": "ઠ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57632": { "content": "ह", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57633": { "content": "ਗ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57634": { "content": "ੂ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57635": { "content": "ी", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57636": { "content": "।", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57637": { "content": "ਇ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57638": { "content": "ਙ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57639": { "content": "ਸ਼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57640": { "content": "ु", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57641": { "content": "Ḍ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57642": { "content": "આ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57643": { "content": "ਨ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57644": { "content": "क", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57645": { "content": "ट", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57646": { "content": "े", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57647": { "content": "П", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57648": { "content": "ા", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57649": { "content": "ણ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57650": { "content": "і", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57651": { "content": "ਢ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57652": { "content": "ا", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57653": { "content": "ੀ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57654": { "content": "ਝ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57655": { "content": "ૂ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57656": { "content": "1", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57657": { "content": "ਏ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57658": { "content": "ਹ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57659": { "content": "स", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57660": { "content": "ذ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57661": { "content": "਼", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57662": { "content": "ੌ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57663": { "content": "ध", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57664": { "content": "ਓ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57665": { "content": "ਈ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57666": { "content": "ુ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57667": { "content": "ਠ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57668": { "content": "ਖ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57669": { "content": "ं", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57670": { "content": "ਲ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false }, "57671": { "content": "ດ", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": false } }, "additional_special_tokens": [ "", "" ], "bos_token": "", "clean_up_tokenization_spaces": false, "cls_token": "", "eos_token": "", "mask_token": "", "model_max_length": 1000000000000000019884624838656, "pad_token": "", "processor_class": "DonutProcessor", "sep_token": "", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer", "unk_token": "" }