CoolFace
Modelpublic

eventdata-utd/gtd-2016

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes6downloads
tokenizer.json30150 linesDownload Raw Back to root
1{2  "version": "1.0",3  "truncation": null,4  "padding": null,5  "added_tokens": [6    {7      "id": 0,8      "content": "[PAD]",9      "single_word": false,10      "lstrip": false,11      "rstrip": false,12      "normalized": false,13      "special": true14    },15    {16      "id": 1,17      "content": "[UNK]",18      "single_word": false,19      "lstrip": false,20      "rstrip": false,21      "normalized": false,22      "special": true23    },24    {25      "id": 2,26      "content": "[CLS]",27      "single_word": false,28      "lstrip": false,29      "rstrip": false,30      "normalized": false,31      "special": true32    },33    {34      "id": 3,35      "content": "[MASK]",36      "single_word": false,37      "lstrip": false,38      "rstrip": false,39      "normalized": false,40      "special": true41    },42    {43      "id": 4,44      "content": "[SEP]",45      "single_word": false,46      "lstrip": false,47      "rstrip": false,48      "normalized": false,49      "special": true50    }51  ],52  "normalizer": {53    "type": "BertNormalizer",54    "clean_text": true,55    "handle_chinese_chars": true,56    "strip_accents": null,57    "lowercase": true58  },59  "pre_tokenizer": {60    "type": "BertPreTokenizer"61  },62  "post_processor": {63    "type": "TemplateProcessing",64    "single": [65      {66        "SpecialToken": {67          "id": "[CLS]",68          "type_id": 069        }70      },71      {72        "Sequence": {73          "id": "A",74          "type_id": 075        }76      },77      {78        "SpecialToken": {79          "id": "[SEP]",80          "type_id": 081        }82      }83    ],84    "pair": [85      {86        "SpecialToken": {87          "id": "[CLS]",88          "type_id": 089        }90      },91      {92        "Sequence": {93          "id": "A",94          "type_id": 095        }96      },97      {98        "SpecialToken": {99          "id": "[SEP]",100          "type_id": 0101        }102      },103      {104        "Sequence": {105          "id": "B",106          "type_id": 1107        }108      },109      {110        "SpecialToken": {111          "id": "[SEP]",112          "type_id": 1113        }114      }115    ],116    "special_tokens": {117      "[CLS]": {118        "id": "[CLS]",119        "ids": [120          2121        ],122        "tokens": [123          "[CLS]"124        ]125      },126      "[SEP]": {127        "id": "[SEP]",128        "ids": [129          4130        ],131        "tokens": [132          "[SEP]"133        ]134      }135    }136  },137  "decoder": {138    "type": "WordPiece",139    "prefix": "##",140    "cleanup": true141  },142  "model": {143    "type": "WordPiece",144    "unk_token": "[UNK]",145    "continuing_subword_prefix": "##",146    "max_input_chars_per_word": 100,147    "vocab": {148      "[PAD]": 0,149      "[UNK]": 1,150      "[CLS]": 2,151      "[MASK]": 3,152      "[SEP]": 4,153      "!": 5,154      "\"": 6,155      "#": 7,156      "$": 8,157      "%": 9,158      "&": 10,159      "'": 11,160      "(": 12,161      ")": 13,162      "*": 14,163      "+": 15,164      ",": 16,165      "-": 17,166      ".": 18,167      "/": 19,168      "0": 20,169      "1": 21,170      "2": 22,171      "3": 23,172      "4": 24,173      "5": 25,174      "6": 26,175      "7": 27,176      "8": 28,177      "9": 29,178      ":": 30,179      ";": 31,180      "<": 32,181      "=": 33,182      ">": 34,183      "?": 35,184      "@": 36,185      "[": 37,186      "\\": 38,187      "]": 39,188      "^": 40,189      "_": 41,190      "a": 42,191      "b": 43,192      "c": 44,193      "d": 45,194      "e": 46,195      "f": 47,196      "g": 48,197      "h": 49,198      "i": 50,199      "j": 51,200      "k": 52,201      "l": 53,202      "m": 54,203      "n": 55,204      "o": 56,205      "p": 57,206      "q": 58,207      "r": 59,208      "s": 60,209      "t": 61,210      "u": 62,211      "v": 63,212      "w": 64,213      "x": 65,214      "y": 66,215      "z": 67,216      "{": 68,217      "|": 69,218      "}": 70,219      "~": 71,220      "##e": 72,221      "##k": 73,222      "##o": 74,223      "##n": 75,224      "##a": 76,225      "##c": 77,226      "##t": 78,227      "##i": 79,228      "##v": 80,229      "##s": 81,230      "##r": 82,231      "##l": 83,232      "##h": 84,233      "##g": 85,234      "##w": 86,235      "##f": 87,236      "##u": 88,237      "##y": 89,238      "##b": 90,239      "##d": 91,240      "##z": 92,241      "##p": 93,242      "##x": 94,243      "##q": 95,244      "##m": 96,245      "##1": 97,246      "##9": 98,247      "##8": 99,248      "##5": 100,249      "##6": 101,250      "##3": 102,251      "##0": 103,252      "##7": 104,253      "##j": 105,254      "##4": 106,255      "##2": 107,256      "th": 108,257      "##er": 109,258      "the": 110,259      "##in": 111,260      "##on": 112,261      "##ed": 113,262      "##en": 114,263      "##at": 115,264      "##es": 116,265      "##or": 117,266      "##an": 118,267      "in": 119,268      "##ar": 120,269      "##al": 121,270      "##it": 122,271      "of": 123,272      "##ing": 124,273      "an": 125,274      "to": 126,275      "##is": 127,276      "##ou": 128,277      "##ic": 129,278      "##as": 130,279      "##ion": 131,280      "and": 132,281      "##ent": 133,282      "##id": 134,283      "##il": 135,284      "##om": 136,285      "##re": 137,286      "re": 138,287      "##le": 139,288      "##el": 140,289      "##ro": 141,290      "for": 142,291      "be": 143,292      "##ad": 144,293      "on": 145,294      "##ol": 146,295      "sa": 147,296      "##ut": 148,297      "##ur": 149,298      "##st": 150,299      "wh": 151,300      "##ct": 152,301      "st": 153,302      "##ot": 154,303      "##ation": 155,304      "##ve": 156,305      "that": 157,306      "##ig": 158,307      "##ter": 159,308      "##ay": 160,309      "##ce": 161,310      "de": 162,311      "is": 163,312      "##ver": 164,313      "##am": 165,314      "##th": 166,315      "##ir": 167,316      "##ly": 168,317      "he": 169,318      "##ch": 170,319      "##im": 171,320      "said": 172,321      "as": 173,322      "con": 174,323      "was": 175,324      "##se": 176,325      "##ts": 177,326      "##ow": 178,327      "##ment": 179,328      "##ers": 180,329      "al": 181,330      "##ith": 182,331      "##ill": 183,332      "se": 184,333      "at": 185,334      "##ere": 186,335      "##ra": 187,336      "with": 188,337      "##ld": 189,338      "ch": 190,339      "fr": 191,340      "##oun": 192,341      "##est": 193,342      "pro": 194,343      "##et": 195,344      "##us": 196,345      "sh": 197,346      "##ate": 198,347      "pr": 199,348      "un": 200,349      "ne": 201,350      "it": 202,351      "##ul": 203,352      "##un": 204,353      "##op": 205,354      "com": 206,355      "##ess": 207,356      "##ist": 208,357      "##and": 209,358      "by": 210,359      "ha": 211,360      "##pp": 212,361      "##ri": 213,362      "##os": 214,363      "##ac": 215,364      "##ity": 216,365      "##ak": 217,366      "##ge": 218,367      "su": 219,368      "##igh": 220,369      "##ain": 221,370      "le": 222,371      "we": 223,372      "from": 224,373      "##ould": 225,374      "##oc": 226,375      "##ial": 227,376      "not": 228,377      "are": 229,378      "##iv": 230,379      "go": 231,380      "##art": 232,381      "have": 233,382      "##em": 234,383      "ex": 235,384      "##ort": 236,385      "his": 237,386      "##ies": 238,387      "has": 239,388      "##ore": 240,389      "##fic": 241,390      "pol": 242,391      "##pe": 243,392      "##um": 244,393      "##our": 245,394      "##ear": 246,395      "af": 247,396      "##ian": 248,397      "or": 249,398      "##ab": 250,399      "ab": 251,400      "##ud": 252,401      "##day": 253,402      "who": 254,403      "ar": 255,404      "##ia": 256,405      "en": 257,406      "##ast": 258,407      "but": 259,408      "##ive": 260,409      "rep": 261,410      "ag": 262,411      "were": 263,412      "##gh": 264,413      "they": 265,414      "##od": 266,415      "##end": 267,416      "##ary": 268,417      "##ice": 269,418      "##if": 270,419      "##all": 271,420      "had": 272,421      "ad": 273,422      "##ther": 274,423      "this": 275,424      "##ant": 276,425      "##ction": 277,426      "##ust": 278,427      "##00": 279,428      "res": 280,429      "##ich": 281,430      "pe": 282,431      "##ident": 283,432      "##ome": 284,433      "##ap": 285,434      "will": 286,435      "##ie": 287,436      "coun": 288,437      "##ard": 289,438      "##ack": 290,439      "tr": 291,440      "##out": 292,441      "wor": 293,442      "##ber": 294,443      "ac": 295,444      "year": 296,445      "##der": 297,446      "new": 298,447      "offic": 299,448      "pres": 300,449      "##ight": 301,450      "##vern": 302,451      "comm": 303,452      "been": 304,453      "am": 305,454      "pl": 306,455      "govern": 307,456      "##ost": 308,457      "cl": 309,458      "their": 310,459      "##ong": 311,460      "me": 312,461      "##ated": 313,462      "would": 314,463      "##ry": 315,464      "part": 316,465      "19": 317,466      "##ence": 318,467      "##ign": 319,468      "##ag": 320,469      "all": 321,470      "##ations": 322,471      "##ub": 323,472      "##ok": 324,473      "##ell": 325,474      "sp": 326,475      "##ous": 327,476      "cont": 328,477      "##pt": 329,478      "after": 330,479      "which": 331,480      "out": 332,481      "mon": 333,482      "government": 334,483      "inc": 335,484      "##ip": 336,485      "im": 337,486      "##ish": 338,487      "min": 339,488      "##ound": 340,489      "state": 341,490      "##ical": 342,491      "dis": 343,492      "man": 344,493      "##iz": 345,494      "president": 346,495      "tw": 347,496      "##ree": 348,497      "peop": 349,498      "##ough": 350,499      "la": 351,500      "##lic": 352,501      "sec": 353,502      "##ans": 354,503      "##qu": 355,504      "do": 356,505      "people": 357,506      "att": 358,507      "int": 359,508      "##ime": 360,509      "its": 361,510      "up": 362,511      "count": 363,512      "gr": 364,513      "##ition": 365,514      "no": 366,515      "##so": 367,516      "inter": 368,517      "##ure": 369,518      "one": 370,519      "more": 371,520      "about": 372,521      "##ine": 373,522      "us": 374,523      "cr": 375,524      "##ide": 376,525      "over": 377,526      "##ire": 378,527      "acc": 379,528      "also": 380,529      "app": 381,530      "there": 382,531      "##ace": 383,532      "##ates": 384,533      "##ib": 385,534      "comp": 386,535      "ind": 387,536      "two": 388,537      "##ational": 389,538      "##ass": 390,539      "##au": 391,540      "she": 392,541      "##ue": 393,542      "##ict": 394,543      "##ath": 395,544      "##man": 396,545      "can": 397,546      "##ru": 398,547      "##age": 399,548      "##per": 400,549      "##ff": 401,550      "her": 402,551      "##ke": 403,552      "some": 404,553      "so": 405,554      "rec": 406,555      "say": 407,556      "##ks": 408,557      "##ect": 409,558      "per": 410,559      "##ding": 411,560      "##ail": 412,561      "##gr": 413,562      "ser": 414,563      "##ors": 415,564      "##ach": 416,565      "##ose": 417,566      "mar": 418,567      "when": 419,568      "##av": 420,569      "br": 421,570      "police": 422,571      "##ile": 423,572      "##ase": 424,573      "##ublic": 425,574      "##ake": 426,575      "20": 427,576      "ele": 428,577      "ev": 429,578      "##ely": 430,579      "##oth": 431,580      "##ens": 432,581      "other": 433,582      "fir": 434,583      "co": 435,584      "car": 436,585      "##ions": 437,586      "official": 438,587      "mil": 439,588      "##enc": 440,589      "bec": 441,590      "dec": 442,591      "dem": 443,592      "law": 444,593      "##ance": 445,594      "te": 446,595      "##iss": 447,596      "bl": 448,597      "you": 449,598      "lead": 450,599      "##ited": 451,600      "than": 452,601      "cam": 453,602      "##ang": 454,603      "work": 455,604      "war": 456,605      "##own": 457,606      "inv": 458,607      "##eral": 459,608      "again": 460,609      "##itt": 461,610      "##pl": 462,611      "##fer": 463,612      "##for": 464,613      "##ite": 465,614      "li": 466,615      "if": 467,616      "##uc": 468,617      "par": 469,618      "##ade": 470,619      "##ied": 471,620      "##one": 472,621      "##ved": 473,622      "##int": 474,623      "##ister": 475,624      "ro": 476,625      "reg": 477,626      "cour": 478,627      "under": 479,628      "pre": 480,629      "##ally": 481,630      "jo": 482,631      "##ep": 483,632      "them": 484,633      "qu": 485,634      "##wn": 486,635      "em": 487,636      "ass": 488,637      "##ities": 489,638      "##ult": 490,639      "imp": 491,640      "mo": 492,641      "day": 493,642      "hel": 494,643      "##pect": 495,644      "nor": 496,645      "##oup": 497,646      "into": 498,647      "polit": 499,648      "last": 500,649      "##lud": 501,650      "##og": 502,651      "mem": 503,652      "any": 504,653      "him": 505,654      "form": 506,655      "##ey": 507,656      "supp": 508,657      "##orn": 509,658      "report": 510,659      "##ons": 511,660      "milit": 512,661      "spe": 513,662      "##reat": 514,663      "ter": 515,664      "may": 516,665      "##oll": 517,666      "##ues": 518,667      "##ek": 519,668      "dep": 520,669      "##ces": 521,670      "rel": 522,671      "what": 523,672      "could": 524,673      "sc": 525,674      "##ters": 526,675      "call": 527,676      "cons": 528,677      "against": 529,678      "just": 530,679      "bo": 531,680      "##ond": 532,681      "fe": 533,682      "years": 534,683      "first": 535,684      "##uss": 536,685      "##ious": 537,686      "fl": 538,687      "##able": 539,688      "##ents": 540,689      "sch": 541,690      "##ged": 542,691      "##ince": 543,692      "minister": 544,693      "##we": 545,694      "##uring": 546,695      "time": 547,696      "##act": 548,697      "how": 549,698      "act": 550,699      "tra": 551,700      "##ause": 552,701      "includ": 553,702      "kill": 554,703      "##istr": 555,704      "##vel": 556,705      "kn": 557,706      "##urn": 558,707      "##ah": 559,708      "gen": 560,709      "bet": 561,710      "200": 562,711      "sy": 563,712      "def": 564,713      "##ked": 565,714      "##eric": 566,715      "fin": 567,716      "court": 568,717      "vot": 569,718      "sen": 570,719      "group": 571,720      "201": 572,721      "##old": 573,722      "country": 574,723      "sou": 575,724      "rem": 576,725      "ob": 577,726      "##ater": 578,727      "##med": 579,728      "americ": 580,729      "##ild": 581,730      "party": 582,731      "prot": 583,732      "states": 584,733      "national": 585,734      "##ory": 586,735      "our": 587,736      "##ments": 588,737      "united": 589,738      "told": 590,739      "##illion": 591,740      "cent": 592,741      "prov": 593,742      "city": 594,743      "##fore": 595,744      "officials": 596,745      "##li": 597,746      "##rat": 598,747      "000": 599,748      "attack": 600,749      "add": 601,750      "##ings": 602,751      "char": 603,752      "secur": 604,753      "gu": 605,754      "##vers": 606,755      "##ouse": 607,756      "aut": 608,757      "during": 609,758      "lo": 610,759      "election": 611,760      "##gan": 612,761      "des": 613,762      "only": 614,763      "bus": 615,764      "##ood": 616,765      "##ft": 617,766      "str": 618,767      "most": 619,768      "##ution": 620,769      "three": 621,770      "air": 622,771      "because": 623,772      "back": 624,773      "security": 625,774      "##air": 626,775      "now": 627,776      "where": 628,777      "##ran": 629,778      "before": 630,779      "ph": 631,780      "ear": 632,781      "democ": 633,782      "did": 634,783      "high": 635,784      "month": 636,785      "pos": 637,786      "med": 638,787      "news": 639,788      "ma": 640,789      "military": 641,790      "camp": 642,791      "eu": 643,792      "tri": 644,793      "vi": 645,794      "public": 646,795      "intern": 647,796      "political": 648,797      "##cess": 649,798      "##tain": 650,799      "house": 651,800      "##pr": 652,801      "##ord": 653,802      "##min": 654,803      "chin": 655,804      "bel": 656,805      "many": 657,806      "##rael": 658,807      "##bers": 659,808      "##ced": 660,809      "israel": 661,810      "col": 662,811      "##ton": 663,812      "since": 664,813      "leg": 665,814      "tal": 666,815      "##ased": 667,816      "##ency": 668,817      "iss": 669,818      "##ms": 670,819      "while": 671,820      "conf": 672,821      "##ween": 673,822      "ins": 674,823      "plan": 675,824      "between": 676,825      "##ash": 677,826      "should": 678,827      "##ists": 679,828      "##ric": 680,829      "bu": 681,830      "being": 682,831      "##ital": 683,832      "##way": 684,833      "cap": 685,834      "##ision": 686,835      "##cial": 687,836      "ira": 688,837      "##oy": 689,838      "##ret": 690,839      "end": 691,840      "week": 692,841      "##amil": 693,842      "off": 694,843      "##ind": 695,844      "##ating": 696,845      "##hor": 697,846      "po": 698,847      "##lear": 699,848      "invest": 700,849      "former": 701,850      "##me": 702,851      "opp": 703,852      "iraq": 704,853      "##ual": 705,854      "##ery": 706,855      "##ights": 707,856      "##urs": 708,857      "##orts": 709,858      "##other": 710,859      "those": 711,860      "thr": 712,861      "bro": 713,862      "##land": 714,863      "##ph": 715,864      "##ives": 716,865      "##led": 717,866      "##ative": 718,867      "south": 719,868      "wom": 720,869      "##gress": 721,870      "loc": 722,871      "commun": 723,872      "##con": 724,873      "meet": 725,874      "##king": 726,875      "author": 727,876      "ret": 728,877      "serv": 729,878      "mr": 730,879      "ra": 731,880      "##are": 732,881      "don": 733,882      "##ower": 734,883      "democrat": 735,884      "made": 736,885      "get": 737,886      "##hing": 738,887      "##ump": 739,888      "eff": 740,889      "world": 741,890      "support": 742,891      "child": 743,892      "##form": 744,893      "##ise": 745,894      "sur": 746,895      "##ned": 747,896      "##ee": 748,897      "ever": 749,898      "##iew": 750,899      "disc": 751,900      "even": 752,901      "##istan": 753,902      "mu": 754,903      "through": 755,904      "##aking": 756,905      "long": 757,906      "my": 758,907      "pers": 759,908      "cor": 760,909      "such": 761,910      "##res": 762,911      "down": 763,912      "north": 764,913      "sub": 765,914      "##ool": 766,915      "republic": 767,916      "general": 768,917      "fore": 769,918      "##ful": 770,919      "##ians": 771,920      "famil": 772,921      "need": 773,922      "##ission": 774,923      "ann": 775,924      "ban": 776,925      "including": 777,926      "##cent": 778,927      "##und": 779,928      "199": 780,929      "near": 781,930      "like": 782,931      "old": 783,932      "russ": 784,933      "resp": 785,934      "international": 786,935      "##used": 787,936      "##ject": 788,937      "##ty": 789,938      "set": 790,939      "ed": 791,940      "##ward": 792,941      "##ief": 793,942      "found": 794,943      "##rol": 795,944      "##ss": 796,945      "##nes": 797,946      "##ility": 798,947      "##ame": 799,948      "million": 800,949      "##stit": 801,950      "##rib": 802,951      "##ism": 803,952      "members": 804,953      "viol": 805,954      "##ning": 806,955      "##az": 807,956      "##ving": 808,957      "##ording": 809,958      "dire": 810,959      "##ife": 811,960      "hum": 812,961      "ref": 813,962      "prob": 814,963      "sm": 815,964      "terr": 816,965      "ta": 817,966      "killed": 818,967      "school": 819,968      "##hip": 820,969      "cond": 821,970      "##ible": 822,971      "##ior": 823,972      "depart": 824,973      "spok": 825,974      "##ese": 826,975      "then": 827,976      "help": 828,977      "these": 829,978      "op": 830,979      "conc": 831,980      "##ven": 832,981      "stud": 833,982      "foreign": 834,983      "way": 835,984      "sign": 836,985      "##ested": 837,986      "head": 838,987      "contin": 839,988      "according": 840,989      "##ink": 841,990      "##te": 842,991      "##imes": 843,992      "four": 844,993      "investig": 845,994      "##ctor": 846,995      "want": 847,996      "arm": 848,997      "case": 849,998      "trans": 850,999      "##ting": 851,1000      "##ec": 852,1001      "rights": 853,1002      "euro": 854,1003      "take": 855,1004      "##als": 856,1005      "##ges": 857,1006      "oper": 858,1007      "##alth": 859,1008      "##ug": 860,1009      "##ix": 861,1010      "##row": 862,1011      "bar": 863,1012      "says": 864,1013      "well": 865,1014      "id": 866,1015      "##ollow": 867,1016      "own": 868,1017      "##ants": 869,1018      "far": 870,1019      "fed": 871,1020      "##ren": 872,1021      "##ick": 873,1022      "##cil": 874,1023      "leaders": 875,1024      "follow": 876,1025      "called": 877,1026      "percent": 878,1027      "ve": 879,1028      "##aign": 880,1029      "tues": 881,1030      "tuesday": 882,1031      "campaign": 883,1032      "committ": 884,1033      "vis": 885,1034      "##its": 886,1035      "##cc": 887,1036      "##elf": 888,1037      "wed": 889,1038      "##tern": 890,1039      "maj": 891,1040      "##osed": 892,1041      "##les": 893,1042      "soc": 894,1043      "##red": 895,1044      "10": 896,1045      "sever": 897,1046      "pal": 898,1047      "##conom": 899,1048      "##ently": 900,1049      "##ific": 901,1050      "num": 902,1051      "both": 903,1052      "peace": 904,1053      "death": 905,1054      "still": 906,1055      "trump": 907,1056      "sus": 908,1057      "##ene": 909,1058      "econom": 910,1059      "##iday": 911,1060      "reported": 912,1061      "##ison": 913,1062      "make": 914,1063      "##ics": 915,1064      "press": 916,1065      "##ized": 917,1066      "organ": 918,1067      "monday": 919,1068      "human": 920,1069      "polic": 921,1070      "show": 922,1071      "secret": 923,1072      "jud": 924,1073      "##xt": 925,1074      "##ather": 926,1075      "american": 927,1076      "lar": 928,1077      "##ands": 929,1078      "##ral": 930,1079      "##ised": 931,1080      "know": 932,1081      "##gram": 933,1082      "home": 934,1083      "sun": 935,1084      "##leg": 936,1085      "wednes": 937,1086      "wednesday": 938,1087      "china": 939,1088      "every": 940,1089      "department": 941,1090      "##ama": 942,1091      "council": 943,1092      "##ought": 944,1093      "##ries": 945,1094      "ext": 946,1095      "del": 947,1096      "office": 948,1097      "major": 949,1098      "requ": 950,1099      "admin": 951,1100      "##ention": 952,1101      "forces": 953,1102      "##ange": 954,1103      "##ying": 955,1104      "arr": 956,1105      "thurs": 957,1106      "adv": 958,1107      "thursday": 959,1108      "very": 960,1109      "civ": 961,1110      "##io": 962,1111      "another": 963,1112      "##ivers": 964,1113      "##cted": 965,1114      "##velop": 966,1115      "##ctions": 967,1116      "##ular": 968,1117      "power": 969,1118      "appro": 970,1119      "##aim": 971,1120      "##ures": 972,1121      "##ave": 973,1122      "##par": 974,1123      "el": 975,1124      "##att": 976,1125      "##ross": 977,1126      "friday": 978,1127      "chief": 979,1128      "##ament": 980,1129      "sl": 981,1130      "europe": 982,1131      "sent": 983,1132      "##ork": 984,1133      "##ops": 985,1134      "##son": 986,1135      "develop": 987,1136      "administr": 988,1137      "right": 989,1138      "health": 990,1139      "run": 991,1140      "##ued": 992,1141      "est": 993,1142      "##ted": 994,1143      "civil": 995,1144      "##lish": 996,1145      "program": 997,1146      "fire": 998,1147      "main": 999,1148      "prop": 1000,1149      "congress": 1001,1150      "federal": 1002,1151      "san": 1003,1152      "##ern": 1004,1153      "##read": 1005,1154      "##ger": 1006,1155      "put": 1007,1156      "brit": 1008,1157      "vict": 1009,1158      "dif": 1010,1159      "##ploy": 1011,1160      "inf": 1012,1161      "##ense": 1013,1162      "spokes": 1014,1163      "person": 1015,1164      "##omb": 1016,1165      "compan": 1017,1166      "##iet": 1018,1167      "remain": 1019,1168      "exp": 1020,1169      "children": 1021,1170      "##ened": 1022,1171      "washing": 1023,1172      "rele": 1024,1173      "##ling": 1025,1174      "##lin": 1026,1175      "cal": 1027,1176      "leader": 1028,1177      "sat": 1029,1178      "pat": 1030,1179      "washington": 1031,1180      "see": 1032,1181      "har": 1033,1182      "##ov": 1034,1183      "ke": 1035,1184      "going": 1036,1185      "prom": 1037,1186      "pass": 1038,1187      "##ock": 1039,1188      "belie": 1040,1189      "several": 1041,1190      "iran": 1042,1191      "here": 1043,1192      "prev": 1044,1193      "wr": 1045,1194      "women": 1046,1195      "##ever": 1047,1196      "terror": 1048,1197      "claim": 1049,1198      "##rug": 1050,1199      "family": 1051,1200      "##pected": 1052,

Showing the first 1,200 of 30150 lines. Download the file for the rest.