R-08-Transformer-Baseline / tokenizer.json
SentinelHub's picture
Sync corrected public source from GitHub (2026-11-07)
f011463 verified
Raw History Blame Contribute Delete
22.7 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [],
"normalizer": null,
"pre_tokenizer": null,
"post_processor": null,
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"<|end|>": 0,
"<|bos|>": 1,
"<|eos|>": 2,
"<|pad|>": 3,
"<|unk|>": 4,
"<|sep|>": 5,
"<|mask|>": 6,
"<|cls|>": 7,
"<|stop|>": 8,
"<|break|>": 9,
"<spazio>": 10,
"<riga>": 11,
"<tab>": 12,
"<cr>": 13,
"<nbsp>": 14,
"<|system|>": 15,
"<|user|>": 16,
"<|assistant|>": 17,
"<|tu|>": 18,
"<|ai|>": 19,
"<|tool|>": 20,
"<|tool_result|>": 21,
"<|im_start|>": 22,
"<|im_end|>": 23,
"<|db|>": 24,
"<|scheda|>": 25,
"<|indice|>": 26,
"<|sposta|>": 27,
"<|correggi|>": 28,
"<|aggiungi|>": 29,
"<|vuoto|>": 30,
"<|think|>": 31,
"<|/think|>": 32,
"<|appunti|>": 33,
"<|fiducia|>": 34,
"<|chiedo|>": 35,
"<|capito|>": 36,
"<|colonna|>": 37,
"<|hub|>": 38,
"<|cerca|>": 39,
"<|fonte|>": 40,
"<|cita|>": 41,
"<|no_fonte|>": 42,
"<|code|>": 43,
"<|/code|>": 44,
"<|json|>": 45,
"<|lista|>": 46,
"<|tabella|>": 47,
"<|math|>": 48,
"<|url|>": 49,
"<|non_so|>": 50,
"<|esempio|>": 51,
"<|attenzione|>": 52,
"0": 53,
"1": 54,
"2": 55,
"3": 56,
"4": 57,
"5": 58,
"6": 59,
"7": 60,
"8": 61,
"9": 62,
".": 63,
",": 64,
";": 65,
":": 66,
"!": 67,
"?": 68,
"…": 69,
"·": 70,
"'": 71,
"\"": 72,
"«": 73,
"»": 74,
"(": 75,
")": 76,
"[": 77,
"]": 78,
"{": 79,
"}": 80,
"+": 81,
"-": 82,
"*": 83,
"/": 84,
"=": 85,
"<": 86,
">": 87,
"@": 88,
"#": 89,
"%": 90,
"&": 91,
"_": 92,
"|": 93,
"\\": 94,
"^": 95,
"~": 96,
"`": 97,
"$": 98,
"Ͱ": 99,
"ͱ": 100,
"Ͳ": 101,
"ͳ": 102,
"ʹ": 103,
"Ͷ": 104,
"ͷ": 105,
"ͺ": 106,
"ͻ": 107,
"ͼ": 108,
"ͽ": 109,
"Ϳ": 110,
"Ά": 111,
"Έ": 112,
"Ή": 113,
"Ί": 114,
"Ό": 115,
"Ύ": 116,
"Ώ": 117,
"ΐ": 118,
"Α": 119,
"Β": 120,
"Γ": 121,
"Δ": 122,
"Ε": 123,
"Ζ": 124,
"Η": 125,
"Θ": 126,
"Ι": 127,
"Κ": 128,
"Λ": 129,
"Μ": 130,
"Ν": 131,
"Ξ": 132,
"Ο": 133,
"Π": 134,
"Ρ": 135,
"Σ": 136,
"Τ": 137,
"Υ": 138,
"Φ": 139,
"Χ": 140,
"Ψ": 141,
"Ω": 142,
"Ϊ": 143,
"Ϋ": 144,
"ά": 145,
"έ": 146,
"ή": 147,
"ί": 148,
"ΰ": 149,
"α": 150,
"β": 151,
"γ": 152,
"δ": 153,
"ε": 154,
"ζ": 155,
"η": 156,
"θ": 157,
"ι": 158,
"κ": 159,
"λ": 160,
"μ": 161,
"ν": 162,
"ξ": 163,
"ο": 164,
"π": 165,
"ρ": 166,
"ς": 167,
"σ": 168,
"τ": 169,
"υ": 170,
"φ": 171,
"χ": 172,
"ψ": 173,
"ω": 174,
"ϊ": 175,
"ϋ": 176,
"ό": 177,
"ύ": 178,
"ώ": 179,
"Ϗ": 180,
"ϐ": 181,
"ϑ": 182,
"ϒ": 183,
"ϓ": 184,
"ϔ": 185,
"ϕ": 186,
"ϖ": 187,
"ϗ": 188,
"Ϙ": 189,
"ϙ": 190,
"Ϛ": 191,
"ϛ": 192,
"Ϝ": 193,
"ϝ": 194,
"Ϟ": 195,
"ϟ": 196,
"Ϡ": 197,
"ϡ": 198,
"Ϣ": 199,
"ϣ": 200,
"Ϥ": 201,
"ϥ": 202,
"Ϧ": 203,
"ϧ": 204,
"Ϩ": 205,
"ϩ": 206,
"Ϫ": 207,
"ϫ": 208,
"Ϭ": 209,
"ϭ": 210,
"Ϯ": 211,
"ϯ": 212,
"ϰ": 213,
"ϱ": 214,
"ϲ": 215,
"ϳ": 216,
"ϴ": 217,
"ϵ": 218,
"Ϸ": 219,
"ϸ": 220,
"Ϲ": 221,
"Ϻ": 222,
"ϻ": 223,
"ϼ": 224,
"Ͻ": 225,
"Ͼ": 226,
"Ͽ": 227,
"Ѐ": 228,
"Ё": 229,
"Ђ": 230,
"Ѓ": 231,
"Є": 232,
"Ѕ": 233,
"І": 234,
"Ї": 235,
"Ј": 236,
"Љ": 237,
"Њ": 238,
"Ћ": 239,
"Ќ": 240,
"Ѝ": 241,
"Ў": 242,
"Џ": 243,
"А": 244,
"Б": 245,
"В": 246,
"Г": 247,
"Д": 248,
"Е": 249,
"Ж": 250,
"З": 251,
"И": 252,
"Й": 253,
"К": 254,
"Л": 255,
"М": 256,
"Н": 257,
"О": 258,
"П": 259,
"Р": 260,
"С": 261,
"Т": 262,
"У": 263,
"Ф": 264,
"Х": 265,
"Ц": 266,
"Ч": 267,
"Ш": 268,
"Щ": 269,
"Ъ": 270,
"Ы": 271,
"Ь": 272,
"Э": 273,
"Ю": 274,
"Я": 275,
"а": 276,
"б": 277,
"в": 278,
"г": 279,
"д": 280,
"е": 281,
"ж": 282,
"з": 283,
"и": 284,
"й": 285,
"к": 286,
"л": 287,
"м": 288,
"н": 289,
"о": 290,
"п": 291,
"р": 292,
"с": 293,
"т": 294,
"у": 295,
"ф": 296,
"х": 297,
"ц": 298,
"ч": 299,
"ш": 300,
"щ": 301,
"ъ": 302,
"ы": 303,
"ь": 304,
"э": 305,
"ю": 306,
"я": 307,
"ѐ": 308,
"ё": 309,
"ђ": 310,
"ѓ": 311,
"є": 312,
"ѕ": 313,
"і": 314,
"ї": 315,
"ј": 316,
"љ": 317,
"њ": 318,
"ћ": 319,
"ќ": 320,
"ѝ": 321,
"ў": 322,
"џ": 323,
"Ѡ": 324,
"ѡ": 325,
"Ѣ": 326,
"ѣ": 327,
"Ѥ": 328,
"ѥ": 329,
"Ѧ": 330,
"ѧ": 331,
"Ѩ": 332,
"ѩ": 333,
"Ѫ": 334,
"ѫ": 335,
"Ѭ": 336,
"ѭ": 337,
"Ѯ": 338,
"ѯ": 339,
"Ѱ": 340,
"ѱ": 341,
"Ѳ": 342,
"ѳ": 343,
"Ѵ": 344,
"ѵ": 345,
"Ѷ": 346,
"ѷ": 347,
"Ѹ": 348,
"ѹ": 349,
"Ѻ": 350,
"ѻ": 351,
"Ѽ": 352,
"ѽ": 353,
"Ѿ": 354,
"ѿ": 355,
"Ҁ": 356,
"ҁ": 357,
"Ҋ": 358,
"ҋ": 359,
"Ҍ": 360,
"ҍ": 361,
"Ҏ": 362,
"ҏ": 363,
"Ґ": 364,
"ґ": 365,
"Ғ": 366,
"ғ": 367,
"Ҕ": 368,
"ҕ": 369,
"Җ": 370,
"җ": 371,
"Ҙ": 372,
"ҙ": 373,
"Қ": 374,
"қ": 375,
"Ҝ": 376,
"ҝ": 377,
"Ҟ": 378,
"ҟ": 379,
"Ҡ": 380,
"ҡ": 381,
"Ң": 382,
"ң": 383,
"Ҥ": 384,
"ҥ": 385,
"Ҧ": 386,
"ҧ": 387,
"Ҩ": 388,
"ҩ": 389,
"Ҫ": 390,
"ҫ": 391,
"Ҭ": 392,
"ҭ": 393,
"Ү": 394,
"ү": 395,
"Ұ": 396,
"ұ": 397,
"Ҳ": 398,
"ҳ": 399,
"Ҵ": 400,
"ҵ": 401,
"Ҷ": 402,
"ҷ": 403,
"Ҹ": 404,
"ҹ": 405,
"Һ": 406,
"һ": 407,
"Ҽ": 408,
"ҽ": 409,
"Ҿ": 410,
"ҿ": 411,
"Ӏ": 412,
"Ӂ": 413,
"ӂ": 414,
"Ӄ": 415,
"ӄ": 416,
"Ӆ": 417,
"ӆ": 418,
"Ӈ": 419,
"ӈ": 420,
"Ӊ": 421,
"ӊ": 422,
"Ӌ": 423,
"ӌ": 424,
"Ӎ": 425,
"ӎ": 426,
"ӏ": 427,
"Ӑ": 428,
"ӑ": 429,
"Ӓ": 430,
"ӓ": 431,
"Ӕ": 432,
"ӕ": 433,
"Ӗ": 434,
"ӗ": 435,
"Ә": 436,
"ә": 437,
"Ӛ": 438,
"ӛ": 439,
"Ӝ": 440,
"ӝ": 441,
"Ӟ": 442,
"ӟ": 443,
"Ӡ": 444,
"ӡ": 445,
"Ӣ": 446,
"ӣ": 447,
"Ӥ": 448,
"ӥ": 449,
"Ӧ": 450,
"ӧ": 451,
"Ө": 452,
"ө": 453,
"Ӫ": 454,
"ӫ": 455,
"Ӭ": 456,
"ӭ": 457,
"Ӯ": 458,
"ӯ": 459,
"Ӱ": 460,
"ӱ": 461,
"Ӳ": 462,
"ӳ": 463,
"Ӵ": 464,
"ӵ": 465,
"Ӷ": 466,
"ӷ": 467,
"Ӹ": 468,
"ӹ": 469,
"Ӻ": 470,
"ӻ": 471,
"Ӽ": 472,
"ӽ": 473,
"Ӿ": 474,
"ӿ": 475,
"Ԁ": 476,
"ԁ": 477,
"Ԃ": 478,
"ԃ": 479,
"Ԅ": 480,
"ԅ": 481,
"Ԇ": 482,
"ԇ": 483,
"Ԉ": 484,
"ԉ": 485,
"Ԋ": 486,
"ԋ": 487,
"Ԍ": 488,
"ԍ": 489,
"Ԏ": 490,
"ԏ": 491,
"Ԑ": 492,
"ԑ": 493,
"Ԓ": 494,
"ԓ": 495,
"Ԕ": 496,
"ԕ": 497,
"Ԗ": 498,
"ԗ": 499,
"Ԙ": 500,
"ԙ": 501,
"Ԛ": 502,
"ԛ": 503,
"Ԝ": 504,
"ԝ": 505,
"Ԟ": 506,
"ԟ": 507,
"Ԡ": 508,
"ԡ": 509,
"Ԣ": 510,
"ԣ": 511,
"Ԥ": 512,
"ԥ": 513,
"Ԧ": 514,
"ԧ": 515,
"Ԩ": 516,
"ԩ": 517,
"Ԫ": 518,
"ԫ": 519,
"Ԭ": 520,
"ԭ": 521,
"Ԯ": 522,
"ԯ": 523,
"ἀ": 524,
"ἁ": 525,
"ἂ": 526,
"ἃ": 527,
"ἄ": 528,
"ἅ": 529,
"ἆ": 530,
"ἇ": 531,
"Ἀ": 532,
"Ἁ": 533,
"Ἂ": 534,
"Ἃ": 535,
"Ἄ": 536,
"Ἅ": 537,
"Ἆ": 538,
"Ἇ": 539,
"ἐ": 540,
"ἑ": 541,
"ἒ": 542,
"ἓ": 543,
"ἔ": 544,
"ἕ": 545,
"Ἐ": 546,
"Ἑ": 547,
"Ἒ": 548,
"Ἓ": 549,
"Ἔ": 550,
"Ἕ": 551,
"ἠ": 552,
"ἡ": 553,
"ἢ": 554,
"ἣ": 555,
"ἤ": 556,
"ἥ": 557,
"ἦ": 558,
"ἧ": 559,
"Ἠ": 560,
"Ἡ": 561,
"Ἢ": 562,
"Ἣ": 563,
"Ἤ": 564,
"Ἥ": 565,
"Ἦ": 566,
"Ἧ": 567,
"ἰ": 568,
"ἱ": 569,
"ἲ": 570,
"ἳ": 571,
"ἴ": 572,
"ἵ": 573,
"ἶ": 574,
"ἷ": 575,
"Ἰ": 576,
"Ἱ": 577,
"Ἲ": 578,
"Ἳ": 579,
"Ἴ": 580,
"Ἵ": 581,
"Ἶ": 582,
"Ἷ": 583,
"ὀ": 584,
"ὁ": 585,
"ὂ": 586,
"ὃ": 587,
"ὄ": 588,
"ὅ": 589,
"Ὀ": 590,
"Ὁ": 591,
"Ὂ": 592,
"Ὃ": 593,
"Ὄ": 594,
"Ὅ": 595,
"ὐ": 596,
"ὑ": 597,
"ὒ": 598,
"ὓ": 599,
"ὔ": 600,
"ὕ": 601,
"ὖ": 602,
"ὗ": 603,
"Ὑ": 604,
"Ὓ": 605,
"Ὕ": 606,
"Ὗ": 607,
"ὠ": 608,
"ὡ": 609,
"ὢ": 610,
"ὣ": 611,
"ὤ": 612,
"ὥ": 613,
"ὦ": 614,
"ὧ": 615,
"Ὠ": 616,
"Ὡ": 617,
"Ὢ": 618,
"Ὣ": 619,
"Ὤ": 620,
"Ὥ": 621,
"Ὦ": 622,
"Ὧ": 623,
"ὰ": 624,
"ά": 625,
"ὲ": 626,
"έ": 627,
"ὴ": 628,
"ή": 629,
"ὶ": 630,
"ί": 631,
"ὸ": 632,
"ό": 633,
"ὺ": 634,
"ύ": 635,
"ὼ": 636,
"ώ": 637,
"ᾀ": 638,
"ᾁ": 639,
"ᾂ": 640,
"ᾃ": 641,
"ᾄ": 642,
"ᾅ": 643,
"ᾆ": 644,
"ᾇ": 645,
"ᾈ": 646,
"ᾉ": 647,
"ᾊ": 648,
"ᾋ": 649,
"ᾌ": 650,
"ᾍ": 651,
"ᾎ": 652,
"ᾏ": 653,
"ᾐ": 654,
"ᾑ": 655,
"ᾒ": 656,
"ᾓ": 657,
"ᾔ": 658,
"ᾕ": 659,
"ᾖ": 660,
"ᾗ": 661,
"ᾘ": 662,
"ᾙ": 663,
"ᾚ": 664,
"ᾛ": 665,
"ᾜ": 666,
"ᾝ": 667,
"ᾞ": 668,
"ᾟ": 669,
"ᾠ": 670,
"ᾡ": 671,
"ᾢ": 672,
"ᾣ": 673,
"ᾤ": 674,
"ᾥ": 675,
"ᾦ": 676,
"ᾧ": 677,
"ᾨ": 678,
"ᾩ": 679,
"ᾪ": 680,
"ᾫ": 681,
"ᾬ": 682,
"ᾭ": 683,
"ᾮ": 684,
"ᾯ": 685,
"ᾰ": 686,
"ᾱ": 687,
"ᾲ": 688,
"ᾳ": 689,
"ᾴ": 690,
"ᾶ": 691,
"ᾷ": 692,
"Ᾰ": 693,
"Ᾱ": 694,
"Ὰ": 695,
"Ά": 696,
"ᾼ": 697,
"ι": 698,
"ῂ": 699,
"ῃ": 700,
"ῄ": 701,
"ῆ": 702,
"ῇ": 703,
"Ὲ": 704,
"Έ": 705,
"Ὴ": 706,
"Ή": 707,
"ῌ": 708,
"ῐ": 709,
"ῑ": 710,
"ῒ": 711,
"ΐ": 712,
"ῖ": 713,
"ῗ": 714,
"Ῐ": 715,
"Ῑ": 716,
"Ὶ": 717,
"Ί": 718,
"ῠ": 719,
"ῡ": 720,
"ῢ": 721,
"ΰ": 722,
"ῤ": 723,
"ῥ": 724,
"ῦ": 725,
"ῧ": 726,
"Ῠ": 727,
"Ῡ": 728,
"Ὺ": 729,
"Ύ": 730,
"Ῥ": 731,
"ῲ": 732,
"ῳ": 733,
"ῴ": 734,
"ῶ": 735,
"ῷ": 736,
"Ὸ": 737,
"Ό": 738,
"Ὼ": 739,
"Ώ": 740,
"ῼ": 741,
"Ⲁ": 742,
"ⲁ": 743,
"Ⲃ": 744,
"ⲃ": 745,
"Ⲅ": 746,
"ⲅ": 747,
"Ⲇ": 748,
"ⲇ": 749,
"Ⲉ": 750,
"ⲉ": 751,
"Ⲋ": 752,
"ⲋ": 753,
"Ⲍ": 754,
"ⲍ": 755,
"Ⲏ": 756,
"ⲏ": 757,
"Ⲑ": 758,
"ⲑ": 759,
"Ⲓ": 760,
"ⲓ": 761,
"Ⲕ": 762,
"ⲕ": 763,
"Ⲗ": 764,
"ⲗ": 765,
"Ⲙ": 766,
"ⲙ": 767,
"Ⲛ": 768,
"ⲛ": 769,
"Ⲝ": 770,
"ⲝ": 771,
"Ⲟ": 772,
"ⲟ": 773,
"Ⲡ": 774,
"ⲡ": 775,
"Ⲣ": 776,
"ⲣ": 777,
"Ⲥ": 778,
"ⲥ": 779,
"Ⲧ": 780,
"ⲧ": 781,
"Ⲩ": 782,
"ⲩ": 783,
"Ⲫ": 784,
"ⲫ": 785,
"Ⲭ": 786,
"ⲭ": 787,
"Ⲯ": 788,
"ⲯ": 789,
"Ⲱ": 790,
"ⲱ": 791,
"Ⲳ": 792,
"ⲳ": 793,
"Ⲵ": 794,
"ⲵ": 795,
"Ⲷ": 796,
"ⲷ": 797,
"Ⲹ": 798,
"ⲹ": 799,
"Ⲻ": 800,
"ⲻ": 801,
"Ⲽ": 802,
"ⲽ": 803,
"Ⲿ": 804,
"ⲿ": 805,
"Ⳁ": 806,
"ⳁ": 807,
"Ⳃ": 808,
"ⳃ": 809,
"Ⳅ": 810,
"ⳅ": 811,
"Ⳇ": 812,
"ⳇ": 813,
"Ⳉ": 814,
"ⳉ": 815,
"Ⳋ": 816,
"ⳋ": 817,
"Ⳍ": 818,
"ⳍ": 819,
"Ⳏ": 820,
"ⳏ": 821,
"Ⳑ": 822,
"ⳑ": 823,
"Ⳓ": 824,
"ⳓ": 825,
"Ⳕ": 826,
"ⳕ": 827,
"Ⳗ": 828,
"ⳗ": 829,
"Ⳙ": 830,
"ⳙ": 831,
"Ⳛ": 832,
"ⳛ": 833,
"Ⳝ": 834,
"ⳝ": 835,
"Ⳟ": 836,
"ⳟ": 837,
"Ⳡ": 838,
"ⳡ": 839,
"Ⳣ": 840,
"ⳣ": 841,
"ⳤ": 842,
"Ⳬ": 843,
"ⳬ": 844,
"Ⳮ": 845,
"ⳮ": 846,
"Ⳳ": 847,
"ⳳ": 848,
"Ꙁ": 849,
"ꙁ": 850,
"Ꙃ": 851,
"ꙃ": 852,
"Ꙅ": 853,
"ꙅ": 854,
"Ꙇ": 855,
"ꙇ": 856,
"Ꙉ": 857,
"ꙉ": 858,
"Ꙋ": 859,
"ꙋ": 860,
"Ꙍ": 861,
"ꙍ": 862,
"Ꙏ": 863,
"ꙏ": 864,
"Ꙑ": 865,
"ꙑ": 866,
"Ꙓ": 867,
"ꙓ": 868,
"Ꙕ": 869,
"ꙕ": 870,
"Ꙗ": 871,
"ꙗ": 872,
"Ꙙ": 873,
"ꙙ": 874,
"Ꙛ": 875,
"ꙛ": 876,
"Ꙝ": 877,
"ꙝ": 878,
"Ꙟ": 879,
"ꙟ": 880,
"Ꙡ": 881,
"ꙡ": 882,
"Ꙣ": 883,
"ꙣ": 884,
"Ꙥ": 885,
"ꙥ": 886,
"Ꙧ": 887,
"ꙧ": 888,
"Ꙩ": 889,
"ꙩ": 890,
"Ꙫ": 891,
"ꙫ": 892,
"Ꙭ": 893,
"ꙭ": 894,
"ꙮ": 895,
"ꙿ": 896,
"Ꚁ": 897,
"ꚁ": 898,
"Ꚃ": 899,
"ꚃ": 900,
"Ꚅ": 901,
"ꚅ": 902,
"Ꚇ": 903,
"ꚇ": 904,
"Ꚉ": 905,
"ꚉ": 906,
"Ꚋ": 907,
"ꚋ": 908,
"Ꚍ": 909,
"ꚍ": 910,
"Ꚏ": 911,
"ꚏ": 912,
"Ꚑ": 913,
"ꚑ": 914,
"Ꚓ": 915,
"ꚓ": 916,
"Ꚕ": 917,
"ꚕ": 918,
"Ꚗ": 919,
"ꚗ": 920,
"Ꚙ": 921,
"ꚙ": 922,
"Ꚛ": 923,
"ꚛ": 924,
"ꚜ": 925,
"ꚝ": 926,
"ᲀ": 927,
"ᲁ": 928,
"ᲂ": 929,
"ᲃ": 930,
"ᲄ": 931,
"ᲅ": 932,
"ᲆ": 933,
"ᲇ": 934,
"ᲈ": 935,
"Ա": 936,
"Բ": 937,
"Գ": 938,
"Դ": 939,
"Ե": 940,
"Զ": 941,
"Է": 942,
"Ը": 943,
"Թ": 944,
"Ժ": 945,
"Ի": 946,
"Լ": 947,
"Խ": 948,
"Ծ": 949,
"Կ": 950,
"Հ": 951,
"Ձ": 952,
"Ղ": 953,
"Ճ": 954,
"Մ": 955,
"Յ": 956,
"Ն": 957,
"Շ": 958,
"Ո": 959,
"Չ": 960,
"Պ": 961,
"Ջ": 962,
"Ռ": 963,
"Ս": 964,
"Վ": 965,
"Տ": 966,
"Ր": 967,
"Ց": 968,
"Ւ": 969,
"Փ": 970,
"Ք": 971,
"Օ": 972,
"Ֆ": 973,
"ՙ": 974,
"ՠ": 975,
"ա": 976,
"բ": 977,
"գ": 978,
"դ": 979,
"ե": 980,
"զ": 981,
"է": 982,
"ը": 983,
"թ": 984,
"ժ": 985,
"ի": 986,
"լ": 987,
"խ": 988,
"ծ": 989,
"կ": 990,
"հ": 991,
"ձ": 992,
"ղ": 993,
"ճ": 994,
"մ": 995,
"յ": 996,
"ն": 997,
"շ": 998,
"ո": 999,
"A": 1000,
"B": 1001,
"C": 1002,
"D": 1003,
"E": 1004,
"F": 1005,
"G": 1006,
"H": 1007,
"I": 1008,
"J": 1009,
"K": 1010,
"L": 1011,
"M": 1012,
"N": 1013,
"O": 1014,
"P": 1015,
"Q": 1016,
"R": 1017,
"S": 1018,
"T": 1019,
"U": 1020,
"V": 1021,
"W": 1022,
"X": 1023,
"Y": 1024,
"Z": 1025,
"a": 1026,
"b": 1027,
"c": 1028,
"d": 1029,
"e": 1030,
"f": 1031,
"g": 1032,
"h": 1033,
"i": 1034,
"j": 1035,
"k": 1036,
"l": 1037,
"m": 1038,
"n": 1039,
"o": 1040,
"p": 1041,
"q": 1042,
"r": 1043,
"s": 1044,
"t": 1045,
"u": 1046,
"v": 1047,
"w": 1048,
"x": 1049,
"y": 1050,
"z": 1051,
"À": 1052,
"È": 1053,
"É": 1054,
"Ì": 1055,
"Ò": 1056,
"Ù": 1057,
"à": 1058,
"è": 1059,
"é": 1060,
"ì": 1061,
"ò": 1062,
"ù": 1063,
"Ä": 1064,
"ä": 1065,
"Ö": 1066,
"ö": 1067,
"Ü": 1068,
"ü": 1069,
"ß": 1070,
"Ç": 1071,
"ç": 1072,
"Ë": 1073,
"ë": 1074,
"Á": 1075,
"á": 1076,
"Ñ": 1077,
"ñ": 1078,
"Â": 1079,
"il": 1080,
"lo": 1081,
"la": 1082,
"gli": 1083,
"le": 1084,
"un": 1085,
"uno": 1086,
"una": 1087,
"l'": 1088,
"un'": 1089,
"ad": 1090,
"di": 1091,
"d'": 1092,
"da": 1093,
"in": 1094,
"con": 1095,
"su": 1096,
"per": 1097,
"tra": 1098,
"fra": 1099,
"del": 1100,
"dello": 1101,
"della": 1102,
"dei": 1103,
"degli": 1104,
"delle": 1105,
"dell'": 1106,
"al": 1107,
"allo": 1108,
"alla": 1109,
"ai": 1110,
"agli": 1111,
"alle": 1112,
"all'": 1113,
"dal": 1114,
"dallo": 1115,
"dalla": 1116,
"dai": 1117,
"dagli": 1118,
"dalle": 1119,
"dall'": 1120,
"nel": 1121,
"nello": 1122,
"nella": 1123,
"nei": 1124,
"negli": 1125,
"nelle": 1126,
"nell'": 1127,
"sul": 1128,
"sullo": 1129,
"sulla": 1130,
"sui": 1131,
"sugli": 1132,
"sulle": 1133,
"sull'": 1134,
"ed": 1135,
"oppure": 1136,
"ma": 1137,
"però": 1138,
"bensì": 1139,
"se": 1140,
"che": 1141,
"perché": 1142,
"quando": 1143,
"mentre": 1144,
"quindi": 1145,
"dunque": 1146,
"ossia": 1147,
"cioè": 1148,
"né": 1149,
"io": 1150,
"tu": 1151,
"lui": 1152,
"lei": 1153,
"noi": 1154,
"voi": 1155,
"loro": 1156,
"me": 1157,
"te": 1158,
"sé": 1159,
"mi": 1160,
"ti": 1161,
"ci": 1162,
"vi": 1163,
"si": 1164,
"li": 1165,
"ne": 1166,
"ce": 1167,
"ve": 1168,
"m'": 1169,
"t'": 1170,
"c'": 1171,
"v'": 1172,
"s'": 1173,
"n'": 1174,
"gl'": 1175,
"glielo": 1176,
"gliela": 1177,
"glieli": 1178,
"gliele": 1179,
"gliel'": 1180,
"questo": 1181,
"questa": 1182,
"questi": 1183,
"queste": 1184,
"quest'": 1185,
"quello": 1186,
"quella": 1187,
"quelli": 1188,
"quelle": 1189,
"quell'": 1190,
"ciò": 1191,
"chi": 1192,
"cui": 1193,
"qual": 1194,
"quale": 1195,
"quali": 1196,
"non": 1197,
"essere": 1198,
"esser": 1199,
"sono": 1200,
"sei": 1201,
"siamo": 1202,
"siete": 1203,
"era": 1204,
"stato": 1205,
"stata": 1206,
"stati": 1207,
"state": 1208,
"avere": 1209,
"aver": 1210,
"ho": 1211,
"hai": 1212,
"ha": 1213,
"abbiamo": 1214,
"avete": 1215,
"hanno": 1216,
"avuto": 1217,
"potere": 1218,
"posso": 1219,
"puoi": 1220,
"può": 1221,
"possiamo": 1222,
"potete": 1223,
"possono": 1224,
"dovere": 1225,
"devo": 1226,
"devi": 1227,
"deve": 1228,
"dobbiamo": 1229,
"dovete": 1230,
"devono": 1231,
"volere": 1232,
"voglio": 1233,
"vuoi": 1234,
"vuole": 1235,
"vogliamo": 1236,
"volete": 1237,
"vogliono": 1238,
"più": 1239,
"meno": 1240,
"molto": 1241,
"poco": 1242,
"già": 1243,
"ancora": 1244,
"sempre": 1245,
"mai": 1246,
"anche": 1247,
"solo": 1248,
"come": 1249,
"dove": 1250
},
"unk_token": "<|unk|>"
}
}