colesimmons's picture
Upload tokenizer
b2de666 verified
raw
history blame contribute delete
No virus
39.1 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "<mask>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "\n",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 6,
"content": "<SURFACE>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 7,
"content": "<COLUMN>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 8,
"content": "<BLANK_SPACE>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 9,
"content": "<RULING>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 10,
"content": "...",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Sequence",
"pretokenizers": [
{
"type": "Metaspace",
"replacement": "▁",
"prepend_scheme": "always",
"split": true
},
{
"type": "Punctuation",
"behavior": "Isolated"
}
]
},
"post_processor": {
"type": "RobertaProcessing",
"sep": [
"</s>",
2
],
"cls": [
"<s>",
0
],
"trim_offsets": true,
"add_prefix_space": true
},
"decoder": {
"type": "BPEDecoder",
"suffix": "</w>"
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"<s>": 0,
"<pad>": 1,
"</s>": 2,
"<unk>": 3,
"<mask>": 4,
"\n": 5,
"<SURFACE>": 6,
"<COLUMN>": 7,
"<BLANK_SPACE>": 8,
"<RULING>": 9,
"...": 10,
"&": 11,
"(": 12,
")": 13,
"+": 14,
"-": 15,
".": 16,
"/": 17,
"1": 18,
"2": 19,
"3": 20,
"4": 21,
"5": 22,
"6": 23,
"7": 24,
"8": 25,
"9": 26,
"@": 27,
"A": 28,
"B": 29,
"D": 30,
"E": 31,
"G": 32,
"H": 33,
"I": 34,
"K": 35,
"L": 36,
"M": 37,
"N": 38,
"P": 39,
"R": 40,
"S": 41,
"T": 42,
"U": 43,
"W": 44,
"X": 45,
"Z": 46,
"a": 47,
"b": 48,
"d": 49,
"e": 50,
"f": 51,
"g": 52,
"h": 53,
"i": 54,
"k": 55,
"l": 56,
"m": 57,
"n": 58,
"o": 59,
"p": 60,
"q": 61,
"r": 62,
"s": 63,
"t": 64,
"u": 65,
"w": 66,
"y": 67,
"z": 68,
"{": 69,
"|": 70,
"}": 71,
"~": 72,
"×": 73,
"ŋ": 74,
"Š": 75,
"š": 76,
"ʾ": 77,
"ṣ": 78,
"ṭ": 79,
"⁻": 80,
"₀": 81,
"₁": 82,
"₂": 83,
"₃": 84,
"₄": 85,
"₅": 86,
"₆": 87,
"₇": 88,
"₈": 89,
"₉": 90,
"ₓ": 91,
"▁": 92,
"iš": 93,
"diš": 94,
"ba": 95,
"▁1": 96,
"ga": 97,
"▁u": 98,
"▁g": 99,
"la": 100,
"in": 101,
"du": 102,
"mu": 103,
"▁s": 104,
"▁š": 105,
"aš": 106,
"▁k": 107,
"▁2": 108,
"lu": 109,
"da": 110,
"ur": 111,
"▁n": 112,
"▁lu": 113,
"▁i": 114,
"▁a": 115,
"▁si": 116,
"▁3": 117,
"eš": 118,
"ri": 119,
"ma": 120,
"gal": 121,
"▁e": 122,
"▁sila": 123,
"ta": 124,
"▁du": 125,
"▁mu": 126,
"▁ba": 127,
"ki": 128,
"▁5": 129,
"na": 130,
"▁šu": 131,
"▁ur": 132,
"▁sila₃": 133,
"n₂": 134,
"ka": 135,
"ni": 136,
"ti": 137,
"ban₂": 138,
"▁4": 139,
"ra": 140,
"geš": 141,
"sa": 142,
"gi": 143,
"▁lugal": 144,
"▁gur": 145,
"e₃": 146,
"in₂": 147,
"rig": 148,
"▁ki": 149,
"barig": 150,
"bi": 151,
"▁lu₂": 152,
"▁gu": 153,
"ku": 154,
"zi": 155,
"▁še": 156,
"▁gin₂": 157,
"en": 158,
"tu": 159,
"a₃": 160,
"▁iti": 161,
"▁sa": 162,
"▁i₃": 163,
"▁dumu": 164,
"gu": 165,
"hu": 166,
"▁ni": 167,
"▁ma": 168,
"li": 169,
"geš₂": 170,
"su": 171,
"▁u₄": 172,
"nu": 173,
"še₃": 174,
"me": 175,
"šu": 176,
"▁nin": 177,
"▁udu": 178,
"maš": 179,
"g₂": 180,
"▁na": 181,
"la₂": 182,
"▁en": 183,
"▁gi": 184,
"kam": 185,
"uš": 186,
"▁e₂": 187,
"si": 188,
"▁kaš": 189,
"▁maš": 190,
"m₂": 191,
"▁6": 192,
"ib": 193,
"▁ninda": 194,
"▁zi": 195,
"gar": 196,
"niŋ": 197,
"niŋin": 198,
"▁šuniŋin": 199,
"ša": 200,
"nin": 201,
"išib": 202,
"₁₀": 203,
"išib₃": 204,
"▁ku": 205,
"▁kišib₃": 206,
"kal": 207,
"zu": 208,
"▁gu₄": 209,
"an": 210,
"za": 211,
"ra₂": 212,
"s₂": 213,
"e₂": 214,
"▁da": 215,
"di": 216,
"▁ša₃": 217,
"suen": 218,
"▁dub": 219,
"▁la₂": 220,
"▁ga": 221,
"gir": 222,
"▁ka": 223,
"l₂": 224,
"▁8": 225,
"▁7": 226,
"hul": 227,
"sar": 228,
"ru": 229,
"₁₁": 230,
"▁nu": 231,
"▁us₂": 232,
"ha": 233,
"▁maš₂": 234,
"▁guruš": 235,
"▁tu": 236,
"▁ugu": 237,
"ri₃": 238,
"▁giri₃": 239,
"▁sag": 240,
"iku": 241,
"em": 242,
"▁ugula": 243,
"sa₆": 244,
"ab": 245,
"▁ab": 246,
"▁niga": 247,
"zem": 248,
"sag": 249,
"bur": 250,
"ša₃": 251,
"▁sila₄": 252,
"bar": 253,
"pa": 254,
"▁su": 255,
"▁a₂": 256,
"bi₂": 257,
"mar": 258,
"din": 259,
"b₅": 260,
"nan": 261,
"▁an": 262,
"lil₂": 263,
"▁ezem": 264,
"▁naga": 265,
"šul": 266,
"▁geš": 267,
"▁nig₂": 268,
"am": 269,
"▁ma₂": 270,
"▁šum₂": 271,
"dab₅": 272,
"šara₂": 273,
"▁ge": 274,
"▁ku₃": 275,
"▁u₃": 276,
"du₃": 277,
"▁di": 278,
"gur": 279,
"▁zi₃": 280,
"gal₂": 281,
"mah": 282,
"i₃": 283,
"um": 284,
"dingir": 285,
"im": 286,
"ke": 287,
"r₂": 288,
"▁ša": 289,
"še": 290,
"me₂": 291,
"▁tug₂": 292,
"hun": 293,
"si₂": 294,
"ke₄": 295,
"▁geme₂": 296,
"ne": 297,
"ʾu": 298,
"da₃": 299,
"▁h": 300,
"li₂": 301,
"ba₆": 302,
"am₃": 303,
"▁in": 304,
"ga₂": 305,
"▁ensi₂": 306,
"lum": 307,
"d₂": 308,
"▁sag₁₀": 309,
"nanna": 310,
"▁za": 311,
"r₃": 312,
"u₂": 313,
"▁igi": 314,
"▁nam": 315,
"kur": 316,
"▁šeš": 317,
"gešʾu": 318,
"▁uri": 319,
"▁zu": 320,
"kkal": 321,
"nun": 322,
"▁u₂": 323,
"▁siki": 324,
"kuₓ": 325,
"DU": 326,
"bu": 327,
"mma": 328,
"▁sar": 329,
"bur₃": 330,
"eše₃": 331,
"▁p": 332,
"▁uri₅": 333,
"▁9": 334,
"ban": 335,
"d₃": 336,
"gi₄": 337,
"gin₂": 338,
"▁hu": 339,
"ina": 340,
"ur₄": 341,
"▁kuš": 342,
"tur": 343,
"du₁₀": 344,
"banda₃": 345,
"▁ab₂": 346,
"nus": 347,
"ku₃": 348,
"ta₂": 349,
"re": 350,
"ku₅": 351,
"lim": 352,
"▁amar": 353,
"ia₃": 354,
"ŋa": 355,
"du₁₁": 356,
"▁im": 357,
"inana": 358,
"▁gub": 359,
"du₈": 360,
"▁ha": 361,
"utu": 362,
"▁ta": 363,
"▁gu₂": 364,
"nigin₂": 365,
"▁dug": 366,
"▁kur": 367,
"▁ud": 368,
"de₃": 369,
"▁gun₂": 370,
"dub": 371,
"▁engar": 372,
"tum": 373,
"mun": 374,
"▁u₈": 375,
"▁la": 376,
"gu₇": 377,
"ge": 378,
"bbar": 379,
"dumu": 380,
"▁bar": 381,
"b₂": 382,
"▁me": 383,
"h₂": 384,
"▁ku₆": 385,
"▁bala": 386,
"▁sukkal": 387,
"▁gal": 388,
"g₄": 389,
"amar": 390,
"tug₂": 391,
"uz": 392,
"zal": 393,
"kim": 394,
"mi": 395,
"us₂": 396,
"nig₂": 397,
"bin": 398,
"▁er": 399,
"eš₃": 400,
"▁kas": 401,
"▁mar": 402,
"▁al": 403,
"mu₂": 404,
"▁sa₂": 405,
"eš₂": 406,
"▁maškim": 407,
"▁dabin": 408,
"▁ud₅": 409,
"▁uš": 410,
"sag₁₁": 411,
"▁bi₂": 412,
"▁he₂": 413,
"ši": 414,
"nigar": 415,
"▁dam": 416,
"uzur₄": 417,
"▁hi": 418,
"▁inim": 419,
"▁puzur₄": 420,
"▁bad₃": 421,
"g₁": 422,
"gin": 423,
"babbar": 424,
"▁dingir": 425,
"▁ši": 426,
"tuku": 427,
"lu₂": 428,
"▁kin": 429,
"nanše": 430,
"▁umma": 431,
"▁kal": 432,
"lam": 433,
"▁zu₂": 434,
"▁erin₂": 435,
"gar₃": 436,
"iškur": 437,
"gir₂": 438,
"mes": 439,
"lu₅": 440,
"nga": 441,
"▁sipa": 442,
"z₂": 443,
"l₃": 444,
"numun": 445,
"dam": 446,
"▁ziz₂": 447,
"uš₂": 448,
"▁ad": 449,
"dim": 450,
"▁dida": 451,
"un": 452,
"ig": 453,
"▁unu": 454,
"hal": 455,
"▁ak": 456,
"gigir": 457,
"ur₂": 458,
"▁šuš": 459,
"al": 460,
"g₃": 461,
"munus": 462,
"dim₂": 463,
"▁iri": 464,
"lamma": 465,
"▁gal₂": 466,
"gid₂": 467,
"num₂": 468,
"si₄": 469,
"gur₈": 470,
"▁mah": 471,
"pa₃": 472,
"▁anše": 473,
"šubur": 474,
"▁diri": 475,
"sig₁": 476,
"▁eri": 477,
"li₉": 478,
"▁šab": 479,
"▁munus": 480,
"ne₂": 481,
"▁šabra": 482,
"▁id": 483,
"gur₂": 484,
"haldim": 485,
"uda": 486,
"ŋ₂": 487,
"▁i₇": 488,
"dar": 489,
"gin₇": 490,
"▁eridu": 491,
"ga₃": 492,
"šum₂": 493,
"gan": 494,
"de₂": 495,
"▁pa": 496,
"ar": 497,
"▁gid₂": 498,
"limmu₂": 499,
"ak": 500,
"▁ŋ": 501,
"lam₂": 502,
"har": 503,
"▁ti": 504,
"ri₆": 505,
"nita₂": 506,
"▁limmu₂": 507,
"šen": 508,
"pi": 509,
"▁gaba": 510,
"gu₂": 511,
"u₁₀": 512,
"šar₂": 513,
"lugal": 514,
"ŋu₁₀": 515,
"▁nita": 516,
"kiri₆": 517,
"ŋa₂": 518,
"gu₄": 519,
"▁nita₂": 520,
"igi": 521,
"aš₂": 522,
"▁ub": 523,
"siki": 524,
"ri₂": 525,
"▁sanga": 526,
"bala": 527,
"▁z": 528,
"▁šuš₃": 529,
"▁ug₃": 530,
"▁kas₄": 531,
"₁₈": 532,
"de": 533,
"u₃": 534,
"▁gen": 535,
"iri": 536,
"ur₃": 537,
"bru": 538,
"sa₂": 539,
"▁kuš₃": 540,
"▁aga₃": 541,
"▁ama": 542,
"▁guru": 543,
"₁₇": 544,
"kar": 545,
"▁bi": 546,
"▁nibru": 547,
"₁₃": 548,
"kuš": 549,
"▁ga₂": 550,
"▁tur": 551,
"▁eš": 552,
"ezem": 553,
"▁kar": 554,
"iti": 555,
"ru₂": 556,
"a₂": 557,
"▁tu₇": 558,
"▁ne": 559,
"kur₂": 560,
"hur": 561,
"▁du₁₁": 562,
"▁aš": 563,
"▁m": 564,
"sal": 565,
"du₇": 566,
"e₁₁": 567,
"ku₆": 568,
"ir": 569,
"unu": 570,
"pin": 571,
"ag₂": 572,
"tar": 573,
"inim": 574,
"sag₁₀": 575,
"ar₃": 576,
"ŋal₂": 577,
"de₆": 578,
"sir₂": 579,
"▁ur₅": 580,
"nu₄": 581,
"▁sagi": 582,
"ma₂": 583,
"lla": 584,
"h₅": 585,
"hi": 586,
"▁li": 587,
"guz": 588,
"ka₉": 589,
"▁zabar": 590,
"▁munu₄": 591,
"il₂": 592,
"nam": 593,
"unu₆": 594,
"he₂": 595,
"▁šuku": 596,
"nir": 597,
"▁ku₅": 598,
"gaš": 599,
"alim": 600,
"uruda": 601,
"ušda": 602,
"sig₁₅": 603,
"tukul": 604,
"▁ge₆": 605,
"▁duh": 606,
"be": 607,
"▁kurušda": 608,
"bil": 609,
"▁za₃": 610,
"wa": 611,
"▁sig₄": 612,
"te": 613,
"tin": 614,
"muhaldim": 615,
"▁e₃": 616,
"▁kir": 617,
"tara": 618,
"gen": 619,
"▁gir₂": 620,
"ištara": 621,
"er": 622,
"ištaran": 623,
"▁kir₁₁": 624,
"▁am": 625,
"▁dur₃": 626,
"ub": 627,
"▁min": 628,
"bu₃": 629,
"burʾu": 630,
"tim": 631,
"mušen": 632,
"▁ri": 633,
"▁niŋ₂": 634,
"▁sahar": 635,
"tab": 636,
"▁gukkal": 637,
"skur₂": 638,
"ru₅": 639,
"₁₂": 640,
"ken": 641,
"uh₂": 642,
"▁ib₂": 643,
"▁šitim": 644,
"▁gu₃": 645,
"▁gar": 646,
"▁uš₂": 647,
"▁eša": 648,
"▁šag₄": 649,
"▁mah₂": 650,
"▁du₆": 651,
"▁saŋ": 652,
"gub": 653,
"ri₁₇": 654,
"▁kug": 655,
"▁lagaš": 656,
"eš₁₈": 657,
"kken": 658,
"gaba": 659,
"u₄": 660,
"anna": 661,
"šar": 662,
"le": 663,
"su₇": 664,
"▁eš₃": 665,
"▁kun": 666,
"kin": 667,
"ŋar": 668,
"▁esir₂": 669,
"▁gu₇": 670,
"▁ugu₂": 671,
"▁du₁₀": 672,
"san": 673,
"▁du₃": 674,
"▁siskur₂": 675,
"mug": 676,
"▁ra": 677,
"inanna": 678,
"▁pi": 679,
"sig₁₇": 680,
"▁gudu": 681,
"bir": 682,
"▁gi₄": 683,
"▁nindan": 684,
"h₃": 685,
"▁muhaldim": 686,
"ŋiš": 687,
"be₂": 688,
"lal₃": 689,
"▁se": 690,
"▁bur": 691,
"▁gudu₄": 692,
"gada": 693,
"▁du₈": 694,
"▁nesag": 695,
"▁babbar": 696,
"su₂": 697,
"▁ni₂": 698,
"▁pa₄": 699,
"▁gig": 700,
"dul": 701,
"▁dal": 702,
"ul": 703,
"lah₅": 704,
"▁šah₂": 705,
"▁uruda": 706,
"at": 707,
"abzu": 708,
"▁mi": 709,
"šub": 710,
"▁su₃": 711,
"▁ur₃": 712,
"IN": 713,
"di₃": 714,
"saŋ": 715,
"edin": 716,
"mgir": 717,
"id": 718,
"udu": 719,
"▁um": 720,
"▁guru₇": 721,
"apin": 722,
"dli": 723,
"▁ur₂": 724,
"▁gurum₂": 725,
"▁hun": 726,
"lagar": 727,
"ge₆": 728,
"anše": 729,
"sila": 730,
"▁didli": 731,
"▁elam": 732,
"na₄": 733,
"giri₁₇": 734,
"▁šimaš": 735,
"er₃": 736,
"▁šušin": 737,
"▁pisan": 738,
"zla": 739,
"sal₄": 740,
"urₓ": 741,
"▁gada": 742,
"gab": 743,
"dug₄": 744,
"rum": 745,
"▁šimašgi": 746,
"▁gala": 747,
"r₄": 748,
"kun": 749,
"llat": 750,
"duru₅": 751,
"▁tab": 752,
"▁kaskal": 753,
"▁ses": 754,
"šum": 755,
"eb": 756,
"▁unu₃": 757,
"ku₄": 758,
"▁ara": 759,
"▁šim": 760,
"illat": 761,
"▁nar": 762,
"▁zid": 763,
"sukkal": 764,
"dara": 765,
"▁sa₆": 766,
"gur₁₁": 767,
"▁tum": 768,
"tum₂": 769,
"sa₁₀": 770,
"su₃": 771,
"ur₅": 772,
"ama": 773,
"▁ašgab": 774,
"kas": 775,
"ib₂": 776,
"▁šar₃": 777,
"ŋir": 778,
"ad": 779,
"dun": 780,
"uru": 781,
"▁apin": 782,
"▁kur₂": 783,
"n₃": 784,
"qar": 785,
"zlag₂": 786,
"▁ka₅": 787,
"gara₂": 788,
"ppi": 789,
"ŠE": 790,
"dug": 791,
"▁dab₅": 792,
"gul": 793,
"▁kab₂": 794,
"iq": 795,
"▁hul": 796,
"▁be": 797,
"▁ša₁₃": 798,
"▁bara₂": 799,
"muš": 800,
"du₅": 801,
"▁muš": 802,
"▁nagar": 803,
"nesag": 804,
"tuš": 805,
"▁gibil": 806,
"▁hur": 807,
"▁ra₂": 808,
"ru₁₃": 809,
"▁sa₁₀": 810,
"eš₅": 811,
"par₄": 812,
"eri": 813,
"▁nimgir": 814,
"▁bappi": 815,
"ašhur": 816,
"▁sig₁": 817,
"▁sig": 818,
"il": 819,
"am₆": 820,
"dul₅": 821,
"LI": 822,
"bad₃": 823,
"GI": 824,
"sig": 825,
"▁diŋir": 826,
"nita": 827,
"▁ga₆": 828,
"LIL": 829,
"▁ŋi": 830,
"▁keš₂": 831,
"▁sig₁₅": 832,
"GA": 833,
"▁ar": 834,
"šah₂": 835,
"sud₃": 836,
"kke": 837,
"kken₂": 838,
"lunga": 839,
"guru": 840,
"▁še₃": 841,
"gi₇": 842,
"▁libir": 843,
"▁sa₁₂": 844,
"hašhur": 845,
"▁il₂": 846,
"▁mušen": 847,
"du₆": 848,
"r₇": 849,
"kunga₂": 850,
"k₄": 851,
"šeš": 852,
"dan": 853,
"kišib₃": 854,
"geštin": 855,
"iši": 856,
"▁gab₂": 857,
"▁dusu₂": 858,
"▁kala": 859,
"▁nun": 860,
"ah": 861,
"▁zah₃": 862,
"kuš₂": 863,
"luh": 864,
"▁bu": 865,
"sikil": 866,
"▁arad₂": 867,
"▁numun": 868,
"gam": 869,
"teš₂": 870,
"▁er₃": 871,
"azlag₂": 872,
"kum": 873,
"iši₁₇": 874,
"tam": 875,
"▁uru": 876,
"KIN": 877,
"▁bu₃": 878,
"dab": 879,
"▁geštin": 880,
"▁nigar": 881,
"guru₇": 882,
"šu₂": 883,
"se₃": 884,
"sur": 885,
"▁tuš": 886,
"sila₃": 887,
"dara₃": 888,
"dur": 889,
"▁mun": 890,
"▁ŋiš": 891,
"▁eme": 892,
"▁sumun": 893,
"▁simug": 894,
"huš": 895,
"mur": 896,
"▁had₂": 897,
"ŋ₃": 898,
"pi₄": 899,
"▁am₃": 900,
"▁de₆": 901,
"▁kalam": 902,
"▁šar": 903,
"IGI": 904,
"▁šul": 905,
"kiši₁₇": 906,
"tag": 907,
"kar₂": 908,
"ŋeš": 909,
"peš₃": 910,
"▁mur": 911,
"nu₂": 912,
"▁tir": 913,
"▁ku₄": 914,
"▁dug₄": 915,
"sun₂": 916,
"▁dara": 917,
"▁muru₁₃": 918,
"sakar": 919,
"babbar₂": 920,
"bara₂": 921,
"urta": 922,
"erim₂": 923,
"▁babbar₂": 924,
"silim": 925,
"▁nin₉": 926,
"gibil": 927,
"ninda": 928,
"nam₂": 929,
"ze₂": 930,
"gaz": 931,
"dul₃": 932,
"mud": 933,
"gab₂": 934,
"▁gurdub": 935,
"til₃": 936,
"tum₃": 937,
"kab": 938,
"saba": 939,
"▁aŋ₂": 940,
"ŋi": 941,
"šim": 942,
"▁kikken₂": 943,
"p₄": 944,
"▁uz": 945,
"▁gir": 946,
"kup₄": 947,
"su₄": 948,
"▁har": 949,
"▁kuₓ": 950,
"▁duru₅": 951,
"▁eš₂": 952,
"nisaba": 953,
"nag": 954,
"gina": 955,
"sin₂": 956,
"suh₅": 957,
"▁šubur": 958,
"▁šar₂": 959,
"za₃": 960,
"dur₂": 961,
"gin₃": 962,
"▁abzu": 963,
"▁mes": 964,
"▁dara₄": 965,
"keš₂": 966,
"▁zar₃": 967,
"▁šagina": 968,
"kud": 969,
"ninnu": 970,
"we": 971,
"▁ze₂": 972,
"▁šeg": 973,
"LA": 974,
"▁tar": 975,
"kas₄": 976,
"▁sal": 977,
"▁dug₃": 978,
"gin₆": 979,
"▁utu": 980,
"▁nir": 981,
"▁tak₄": 982,
"hen": 983,
"mun₂": 984,
"ug": 985,
"▁gun₃": 986,
"▁imga": 987,
"hendur": 988,
"▁ziₓ": 989,
"▁sag₉": 990,
"▁ŋeš": 991,
"▁dagal": 992,
"gil": 993,
"▁kalag": 994,
"til": 995,
"▁imgaga₃": 996,
"₁₄": 997,
"kikken": 998,
"▁lum": 999,
"šuba": 1000,
"▁nigin₂": 1001,
"▁ag": 1002,
"▁gan": 1003,
"▁egir": 1004,
"▁tuku": 1005,
"▁tag": 1006,
"▁kam": 1007,
"dag": 1008,
"▁šeg₉": 1009,
"₁₆": 1010,
"▁ar₃": 1011,
"gur₄": 1012,
"tir": 1013,
"qu₂": 1014,
"ŋir₂": 1015,
"gu₃": 1016,
"▁na₄": 1017,
"▁tul₂": 1018,
"▁iš": 1019,
"kaskal": 1020,
"▁ib": 1021,
"▁zag": 1022,
"aŋ₂": 1023
},
"merges": [
"i š",
"d iš",
"b a",
"▁ 1",
"g a",
"▁ u",
"▁ g",
"l a",
"i n",
"d u",
"m u",
"▁ s",
"▁ š",
"a š",
"▁ k",
"▁ 2",
"l u",
"d a",
"u r",
"▁ n",
"▁ lu",
"▁ i",
"▁ a",
"▁s i",
"▁ 3",
"e š",
"r i",
"m a",
"ga l",
"▁ e",
"▁si la",
"t a",
"▁ du",
"▁ mu",
"▁ ba",
"k i",
"▁ 5",
"n a",
"▁š u",
"▁u r",
"▁sila ₃",
"n ₂",
"k a",
"n i",
"t i",
"ba n₂",
"▁ 4",
"r a",
"g eš",
"s a",
"g i",
"▁lu gal",
"▁g ur",
"e ₃",
"in ₂",
"ri g",
"▁k i",
"ba rig",
"b i",
"▁lu ₂",
"▁g u",
"k u",
"z i",
"▁š e",
"▁g in₂",
"e n",
"t u",
"a ₃",
"▁i ti",
"▁s a",
"▁i ₃",
"▁du mu",
"g u",
"h u",
"▁n i",
"▁ ma",
"l i",
"geš ₂",
"s u",
"▁u ₄",
"n u",
"š e₃",
"m e",
"š u",
"▁n in",
"▁u du",
"m aš",
"g ₂",
"▁n a",
"la ₂",
"▁e n",
"▁g i",
"ka m",
"u š",
"▁e ₂",
"s i",
"▁k aš",
"▁ maš",
"m ₂",
"▁ 6",
"i b",
"▁nin da",
"▁ zi",
"ga r",
"ni ŋ",
"niŋ in",
"▁šu niŋin",
"š a",
"n in",
"iš ib",
"₁ ₀",
"išib ₃",
"▁k u",
"▁k išib₃",
"ka l",
"z u",
"▁gu ₄",
"a n",
"z a",
"ra ₂",
"s ₂",
"e ₂",
"▁ da",
"d i",
"▁š a₃",
"su en",
"▁du b",
"▁ la₂",
"▁ ga",
"gi r",
"▁k a",
"l ₂",
"▁ 8",
"▁ 7",
"hu l",
"sa r",
"r u",
"₁ ₁",
"▁n u",
"▁u s₂",
"h a",
"▁maš ₂",
"▁gur uš",
"▁ tu",
"▁u gu",
"ri ₃",
"▁gi ri₃",
"▁sa g",
"i ku",
"e m",
"▁ugu la",
"sa ₆",
"a b",
"▁a b",
"▁ni ga",
"z em",
"sa g",
"b ur",
"š a₃",
"▁sila ₄",
"ba r",
"p a",
"▁s u",
"▁a ₂",
"bi ₂",
"ma r",
"d in",
"b ₅",
"na n",
"▁a n",
"li l₂",
"▁e zem",
"▁na ga",
"šu l",
"▁g eš",
"▁ni g₂",
"a m",
"▁ma ₂",
"▁šu m₂",
"da b₅",
"ša ra₂",
"▁g e",
"▁ku ₃",
"▁u ₃",
"du ₃",
"▁ di",
"g ur",
"▁zi ₃",
"gal ₂",
"ma h",
"i ₃",
"u m",
"din gir",
"i m",
"k e",
"r ₂",
"▁š a",
"š e",
"me ₂",
"▁tu g₂",
"hu n",
"si ₂",
"ke ₄",
"▁ge me₂",
"n e",
"ʾ u",
"da ₃",
"▁ h",
"li ₂",
"ba ₆",
"am ₃",
"▁ in",
"ga ₂",
"▁en si₂",
"lu m",
"d ₂",
"▁sag ₁₀",
"nan na",
"▁ za",
"r ₃",
"u ₂",
"▁i gi",
"▁na m",
"k ur",
"▁š eš",
"geš ʾu",
"▁u ri",
"▁ zu",
"k kal",
"nu n",
"▁u ₂",
"▁si ki",
"ku ₓ",
"D U",
"b u",
"m ma",
"▁sa r",
"bur ₃",
"eš e₃",
"▁ p",
"▁uri ₅",
"▁ 9",
"ba n",
"d ₃",
"gi ₄",
"g in₂",
"▁ hu",
"in a",
"ur ₄",
"▁k uš",
"t ur",
"du ₁₀",
"ban da₃",
"▁ab ₂",
"nu s",
"ku ₃",
"ta ₂",
"r e",
"ku ₅",
"li m",
"▁a mar",
"i a₃",
"ŋ a",
"du ₁₁",
"▁i m",
"ina na",
"▁gu b",
"du ₈",
"▁ ha",
"u tu",
"▁ ta",
"▁gu ₂",
"ni gin₂",
"▁du g",
"▁k ur",
"▁u d",
"d e₃",
"▁gu n₂",
"du b",
"▁en gar",
"tu m",
"mu n",
"▁u ₈",
"▁ la",
"gu ₇",
"g e",
"b bar",
"du mu",
"▁ba r",
"b ₂",
"▁ me",
"h ₂",
"▁ku ₆",
"▁ba la",
"▁su kkal",
"▁ gal",
"g ₄",
"a mar",
"tu g₂",
"u z",
"za l",
"ki m",
"m i",
"u s₂",
"ni g₂",
"b in",
"▁e r",
"eš ₃",
"▁ka s",
"▁ma r",
"▁a l",
"mu ₂",
"▁sa ₂",
"eš ₂",
"▁maš kim",
"▁da bin",
"▁ud ₅",
"▁u š",
"sag ₁₁",
"▁ bi₂",
"▁h e₂",
"š i",
"ni gar",
"▁da m",
"uz ur₄",
"▁h i",
"▁in im",
"▁p uzur₄",
"▁ba d₃",
"g ₁",
"g in",
"ba bbar",
"▁ dingir",
"▁š i",
"tu ku",
"lu ₂",
"▁k in",
"nan še",
"▁u mma",
"▁ka l",
"la m",
"▁zu ₂",
"▁er in₂",
"gar ₃",
"iš kur",
"gir ₂",
"me s",
"lu ₅",
"n ga",
"▁si pa",
"z ₂",
"l ₃",
"nu mun",
"da m",
"▁zi z₂",
"uš ₂",
"▁a d",
"di m",
"▁di da",
"u n",
"i g",
"▁u nu",
"ha l",
"▁a k",
"gi gir",
"ur ₂",
"▁šu š",
"a l",
"g ₃",
"mu nus",
"di m₂",
"▁i ri",
"la mma",
"▁ gal₂",
"gi d₂",
"nu m₂",
"si ₄",
"gur ₈",
"▁ma h",
"p a₃",
"▁an še",
"šu bur",
"▁di ri",
"si g₁",
"▁e ri",
"li ₉",
"▁š ab",
"▁mu nus",
"n e₂",
"▁šab ra",
"▁i d",
"gur ₂",
"hal dim",
"u da",
"ŋ ₂",
"▁i ₇",
"da r",
"gin ₇",
"▁eri du",
"ga ₃",
"šu m₂",
"ga n",
"d e₂",
"▁ pa",
"a r",
"▁gi d₂",
"lim mu₂",
"a k",
"▁ ŋ",
"la m₂",
"ha r",
"▁ ti",
"ri ₆",
"ni ta₂",
"▁ limmu₂",
"š en",
"p i",
"▁ga ba",
"gu ₂",
"u ₁₀",
"ša r₂",
"lu gal",
"ŋ u₁₀",
"▁ni ta",
"ki ri₆",
"ŋa ₂",
"gu ₄",
"▁ni ta₂",
"i gi",
"aš ₂",
"▁u b",
"si ki",
"ri ₂",
"▁sa nga",
"ba la",
"▁ z",
"▁šuš ₃",
"▁u g₃",
"▁kas ₄",
"₁ ₈",
"d e",
"u ₃",
"▁g en",
"i ri",
"ur ₃",
"b ru",
"sa ₂",
"▁kuš ₃",
"▁a ga₃",
"▁a ma",
"▁gur u",
"₁ ₇",
"ka r",
"▁ bi",
"▁ni bru",
"₁ ₃",
"ku š",
"▁ga ₂",
"▁ tur",
"▁ eš",
"e zem",
"▁ka r",
"i ti",
"ru ₂",
"a ₂",
"▁tu ₇",
"▁n e",
"kur ₂",
"h ur",
"▁du ₁₁",
"▁ aš",
"▁ m",
"sa l",
"du ₇",
"e ₁₁",
"ku ₆",
"i r",
"u nu",
"p in",
"a g₂",
"ta r",
"in im",
"sag ₁₀",
"a r₃",
"ŋa l₂",
"de ₆",
"si r₂",
"▁ur ₅",
"nu ₄",
"▁sa gi",
"ma ₂",
"l la",
"h ₅",
"h i",
"▁ li",
"gu z",
"ka ₉",
"▁za bar",
"▁mu nu₄",
"i l₂",
"na m",
"unu ₆",
"h e₂",
"▁šu ku",
"ni r",
"▁ku ₅",
"ga š",
"a lim",
"ur uda",
"uš da",
"sig₁ ₅",
"tuku l",
"▁ge ₆",
"▁du h",
"b e",
"▁kur ušda",
"bi l",
"▁z a₃",
"w a",
"▁si g₄",
"t e",
"t in",
"mu haldim",
"▁e ₃",
"▁ki r",
"ta ra",
"g en",
"▁gi r₂",
"iš tara",
"e r",
"ištara n",
"▁kir ₁₁",
"▁a m",
"▁du r₃",
"u b",
"▁m in",
"bu ₃",
"bur ʾu",
"ti m",
"mu šen",
"▁ ri",
"▁ni ŋ₂",
"▁sa har",
"ta b",
"▁gu kkal",
"s kur₂",
"ru ₅",
"₁ ₂",
"k en",
"u h₂",
"▁i b₂",
"▁ši tim",
"▁gu ₃",
"▁ gar",
"▁uš ₂",
"▁eš a",
"▁ša g₄",
"▁ma h₂",
"▁du ₆",
"▁sa ŋ",
"gu b",
"ri ₁₇",
"▁ku g",
"▁la gaš",
"eš ₁₈",
"k ken",
"ga ba",
"u ₄",
"an na",
"ša r",
"l e",
"su ₇",
"▁ eš₃",
"▁ku n",
"k in",
"ŋa r",
"▁e sir₂",
"▁gu ₇",
"▁ugu ₂",
"▁du ₁₀",
"sa n",
"▁du ₃",
"▁si skur₂",
"mu g",
"▁ ra",
"in anna",
"▁p i",
"sig₁ ₇",
"▁gu du",
"bi r",
"▁gi ₄",
"▁ninda n",
"h ₃",
"▁mu haldim",
"ŋ iš",
"b e₂",
"la l₃",
"▁s e",
"▁ bur",
"▁gudu ₄",
"ga da",
"▁du ₈",
"▁ne sag",
"▁ba bbar",
"su ₂",
"▁ni ₂",
"▁pa ₄",
"▁gi g",
"du l",
"▁da l",
"u l",
"la h₅",
"▁ša h₂",
"▁ur uda",
"a t",
"ab zu",
"▁ mi",
"šu b",
"▁su ₃",
"▁ur ₃",
"I N",
"di ₃",
"sa ŋ",
"e din",
"m gir",
"i d",
"u du",
"▁u m",
"▁guru ₇",
"a pin",
"d li",
"▁ur ₂",
"▁guru m₂",
"▁ hun",
"la gar",
"ge ₆",
"an še",
"si la",
"▁di dli",
"▁e lam",
"na ₄",
"gi ri₁₇",
"▁ši maš",
"e r₃",
"▁šuš in",
"▁pi san",
"z la",
"sal ₄",
"ur ₓ",
"▁ga da",
"ga b",
"du g₄",
"ru m",
"▁šimaš gi",
"▁ga la",
"r ₄",
"ku n",
"lla t",
"du ru₅",
"▁ta b",
"▁kas kal",
"▁se s",
"šu m",
"e b",
"▁unu ₃",
"ku ₄",
"▁a ra",
"▁š im",
"i llat",
"▁na r",
"▁zi d",
"su kkal",
"da ra",
"▁sa ₆",
"gur ₁₁",
"▁tu m",
"tu m₂",
"sa ₁₀",
"su ₃",
"ur ₅",
"a ma",
"▁aš gab",
"ka s",
"ib ₂",
"▁ša r₃",
"ŋ ir",
"a d",
"du n",
"ur u",
"▁a pin",
"▁kur ₂",
"n ₃",
"q ar",
"zla g₂",
"▁ka ₅",
"ga ra₂",
"p pi",
"Š E",
"du g",
"▁da b₅",
"gu l",
"▁ka b₂",
"i q",
"▁ hul",
"▁ be",
"▁ša ₁₃",
"▁ba ra₂",
"mu š",
"du ₅",
"▁mu š",
"▁na gar",
"ne sag",
"tu š",
"▁gi bil",
"▁h ur",
"▁ ra₂",
"ru ₁₃",
"▁sa ₁₀",
"eš ₅",
"pa r₄",
"e ri",
"▁ni mgir",
"▁ba ppi",
"aš hur",
"▁si g₁",
"▁si g",
"i l",
"am ₆",
"dul ₅",
"L I",
"ba d₃",
"G I",
"si g",
"▁di ŋir",
"ni ta",
"▁ga ₆",
"LI L",
"▁ŋ i",
"▁k eš₂",
"▁sig₁ ₅",
"G A",
"▁a r",
"ša h₂",
"su d₃",
"k ke",
"kke n₂",
"lu nga",
"gur u",
"▁š e₃",
"gi ₇",
"▁li bir",
"▁sa ₁₂",
"h ašhur",
"▁i l₂",
"▁mu šen",
"du ₆",
"r ₇",
"kun ga₂",
"k ₄",
"š eš",
"da n",
"k išib₃",
"geš tin",
"iš i",
"▁ga b₂",
"▁du su₂",
"▁ka la",
"▁nu n",
"a h",
"▁za h₃",
"kuš ₂",
"lu h",
"▁ bu",
"siki l",
"▁ara d₂",
"▁nu mun",
"ga m",
"t eš₂",
"▁e r₃",
"a zlag₂",
"ku m",
"iši ₁₇",
"ta m",
"▁ur u",
"K IN",
"▁ bu₃",
"da b",
"▁geš tin",
"▁ni gar",
"guru ₇",
"šu ₂",
"s e₃",
"s ur",
"▁tu š",
"sila ₃",
"dara ₃",
"du r",
"▁mu n",
"▁ŋ iš",
"▁e me",
"▁su mun",
"▁si mug",
"hu š",
"mu r",
"▁ha d₂",
"ŋ ₃",
"pi ₄",
"▁am ₃",
"▁ de₆",
"▁ka lam",
"▁ša r",
"I GI",
"▁šu l",
"k iši₁₇",
"ta g",
"ka r₂",
"ŋ eš",
"p eš₃",
"▁mu r",
"nu ₂",
"▁ti r",
"▁ku ₄",
"▁dug ₄",
"su n₂",
"▁da ra",
"▁mu ru₁₃",
"sa kar",
"babbar ₂",
"ba ra₂",
"ur ta",
"eri m₂",
"▁babbar ₂",
"si lim",
"▁nin ₉",
"gi bil",
"nin da",
"na m₂",
"z e₂",
"ga z",
"du l₃",
"mu d",
"ga b₂",
"▁gur dub",
"ti l₃",
"tum ₃",
"ka b",
"sa ba",
"▁a ŋ₂",
"ŋ i",
"š im",
"▁ki kken₂",
"p ₄",
"▁u z",
"▁gi r",
"ku p₄",
"su ₄",
"▁ha r",
"▁ku ₓ",
"▁du ru₅",
"▁ eš₂",
"ni saba",
"na g",
"g ina",
"s in₂",
"su h₅",
"▁šu bur",
"▁ša r₂",
"z a₃",
"du r₂",
"gin ₃",
"▁ab zu",
"▁me s",
"▁dara ₄",
"k eš₂",
"▁za r₃",
"▁ša gina",
"ku d",
"nin nu",
"w e",
"▁z e₂",
"▁še g",
"L A",
"▁ta r",
"kas ₄",
"▁sa l",
"▁dug ₃",
"gin ₆",
"▁u tu",
"▁ni r",
"▁ta k₄",
"h en",
"mu n₂",
"u g",
"▁gu n₃",
"▁im ga",
"hen dur",
"▁zi ₓ",
"▁sag ₉",
"▁ŋ eš",
"▁da gal",
"gi l",
"▁kala g",
"ti l",
"▁imga ga₃",
"₁ ₄",
"ki kken",
"▁lu m",
"šu ba",
"▁ni gin₂",
"▁a g",
"▁ga n",
"▁e gir",
"▁tu ku",
"▁ta g",
"▁ka m",
"da g",
"▁šeg ₉",
"₁ ₆",
"▁a r₃",
"gur ₄",
"ti r",
"q u₂",
"ŋi r₂",
"gu ₃",
"▁na ₄",
"▁tu l₂",
"▁ iš",
"kas kal",
"▁i b",
"▁za g",
"a ŋ₂"
]
}
}