SinQQQ's picture
Upload tokenizer
92bf4be
raw
history blame
11.5 kB
{
"[PAD]": 825,
"[UNK]": 824,
"d": 715,
"|": 465,
"、": 598,
"。": 392,
"《": 552,
"》": 14,
"「": 90,
"」": 741,
"㗎": 224,
"一": 553,
"丈": 506,
"三": 564,
"上": 250,
"下": 45,
"不": 196,
"且": 461,
"世": 809,
"並": 243,
"中": 610,
"丹": 352,
"主": 655,
"久": 279,
"之": 515,
"乎": 183,
"乜": 251,
"九": 617,
"也": 333,
"乾": 212,
"了": 577,
"事": 572,
"二": 81,
"于": 57,
"些": 653,
"亞": 817,
"交": 139,
"京": 350,
"人": 427,
"什": 585,
"今": 671,
"仔": 750,
"他": 604,
"代": 794,
"以": 125,
"仲": 491,
"件": 169,
"任": 140,
"份": 166,
"企": 400,
"伙": 475,
"似": 454,
"但": 419,
"位": 510,
"住": 526,
"何": 173,
"作": 504,
"你": 18,
"佢": 629,
"使": 437,
"來": 503,
"供": 2,
"依": 664,
"便": 24,
"係": 110,
"保": 34,
"信": 566,
"俾": 542,
"個": 484,
"們": 184,
"借": 384,
"值": 497,
"假": 229,
"做": 814,
"傑": 158,
"傢": 66,
"債": 508,
"像": 740,
"億": 726,
"儲": 389,
"元": 793,
"充": 319,
"兇": 642,
"先": 438,
"光": 658,
"免": 591,
"入": 473,
"內": 667,
"全": 91,
"兩": 95,
"八": 500,
"公": 626,
"六": 220,
"共": 303,
"其": 323,
"冇": 388,
"再": 459,
"冤": 494,
"冬": 378,
"冷": 634,
"出": 615,
"分": 7,
"切": 694,
"別": 765,
"到": 707,
"制": 354,
"刷": 746,
"刻": 422,
"前": 782,
"剛": 56,
"功": 255,
"加": 517,
"助": 266,
"勇": 325,
"動": 147,
"務": 818,
"包": 106,
"化": 241,
"北": 479,
"匯": 685,
"區": 433,
"十": 200,
"協": 270,
"博": 59,
"卡": 223,
"即": 648,
"卻": 144,
"去": 632,
"又": 754,
"及": 772,
"友": 293,
"反": 213,
"取": 155,
"受": 578,
"口": 727,
"古": 514,
"句": 736,
"另": 375,
"只": 635,
"叫": 296,
"可": 113,
"台": 557,
"吃": 38,
"各": 595,
"合": 308,
"同": 75,
"名": 807,
"向": 769,
"吓": 691,
"吞": 342,
"否": 85,
"呀": 476,
"告": 788,
"呢": 471,
"味": 407,
"呼": 280,
"命": 238,
"咀": 567,
"咁": 511,
"和": 633,
"咗": 257,
"咩": 197,
"咪": 728,
"哋": 40,
"員": 776,
"哥": 29,
"哩": 496,
"唔": 252,
"售": 404,
"唱": 730,
"啊": 71,
"問": 703,
"啤": 644,
"啦": 78,
"啫": 713,
"啱": 374,
"啲": 369,
"喇": 771,
"喊": 69,
"喎": 171,
"喜": 127,
"喝": 361,
"喺": 3,
"嗰": 237,
"嗱": 322,
"嘅": 148,
"嘢": 305,
"嘴": 714,
"噃": 723,
"器": 269,
"噬": 61,
"嚟": 628,
"嚿": 619,
"四": 373,
"回": 27,
"因": 201,
"國": 253,
"圍": 135,
"園": 600,
"團": 603,
"土": 767,
"在": 128,
"地": 170,
"坐": 187,
"坑": 262,
"型": 456,
"埋": 331,
"城": 47,
"基": 790,
"堅": 334,
"報": 217,
"場": 54,
"塊": 199,
"墓": 371,
"增": 36,
"壞": 177,
"士": 72,
"外": 761,
"多": 777,
"夠": 745,
"大": 525,
"天": 376,
"奈": 513,
"奮": 657,
"她": 785,
"好": 450,
"如": 4,
"妙": 581,
"妹": 554,
"姐": 349,
"姑": 486,
"委": 192,
"婆": 122,
"嬲": 209,
"子": 391,
"字": 412,
"存": 669,
"學": 417,
"它": 580,
"完": 695,
"定": 757,
"宜": 17,
"客": 590,
"家": 822,
"容": 683,
"寃": 233,
"實": 507,
"審": 174,
"封": 558,
"射": 425,
"將": 587,
"對": 605,
"導": 114,
"小": 613,
"尚": 286,
"就": 298,
"尼": 60,
"局": 448,
"居": 709,
"屋": 687,
"屎": 545,
"展": 444,
"屯": 19,
"山": 758,
"島": 393,
"嶼": 501,
"工": 84,
"左": 179,
"差": 482,
"己": 774,
"已": 150,
"巴": 264,
"市": 720,
"常": 186,
"幕": 28,
"幫": 796,
"平": 336,
"年": 364,
"幾": 666,
"底": 821,
"店": 326,
"府": 67,
"度": 609,
"庫": 134,
"康": 819,
"建": 489,
"弊": 15,
"式": 44,
"張": 717,
"強": 677,
"彈": 11,
"形": 194,
"彩": 623,
"影": 665,
"往": 452,
"很": 413,
"律": 358,
"後": 121,
"徑": 443,
"得": 65,
"心": 582,
"快": 188,
"念": 62,
"怒": 522,
"怕": 313,
"思": 137,
"怪": 527,
"息": 616,
"情": 341,
"惠": 395,
"想": 679,
"意": 37,
"愛": 483,
"感": 678,
"慘": 312,
"慢": 639,
"慧": 760,
"慮": 453,
"憑": 143,
"憶": 650,
"懵": 311,
"懷": 338,
"成": 202,
"我": 464,
"或": 806,
"戰": 131,
"戲": 124,
"戶": 519,
"所": 704,
"手": 402,
"才": 327,
"扒": 692,
"打": 108,
"托": 766,
"承": 532,
"把": 663,
"投": 297,
"抗": 87,
"折": 226,
"抵": 630,
"拉": 722,
"拌": 231,
"招": 263,
"拜": 643,
"拿": 492,
"按": 654,
"捨": 420,
"掂": 535,
"排": 516,
"接": 401,
"控": 244,
"推": 268,
"提": 539,
"揚": 415,
"揪": 208,
"搞": 487,
"搭": 357,
"撚": 637,
"撲": 163,
"擊": 55,
"擔": 141,
"擴": 246,
"攪": 394,
"支": 153,
"攰": 467,
"攻": 579,
"放": 529,
"政": 416,
"救": 739,
"散": 536,
"敵": 752,
"數": 159,
"文": 440,
"料": 744,
"新": 548,
"斷": 408,
"方": 178,
"於": 498,
"施": 627,
"旅": 432,
"族": 442,
"既": 411,
"日": 102,
"旦": 688,
"早": 568,
"旬": 699,
"旺": 563,
"明": 112,
"星": 176,
"昨": 540,
"是": 696,
"時": 748,
"晚": 583,
"智": 167,
"曉": 597,
"書": 651,
"最": 698,
"會": 123,
"月": 546,
"有": 96,
"朋": 89,
"服": 353,
"朗": 645,
"望": 689,
"期": 530,
"木": 242,
"未": 97,
"本": 6,
"村": 162,
"杯": 537,
"枉": 602,
"果": 287,
"枝": 340,
"架": 172,
"柏": 164,
"柔": 396,
"柴": 803,
"校": 792,
"桂": 228,
"案": 300,
"梅": 219,
"梨": 711,
"棗": 791,
"棚": 276,
"椒": 593,
"極": 381,
"榜": 207,
"榮": 521,
"樂": 799,
"樣": 105,
"樽": 747,
"機": 561,
"檢": 738,
"檸": 23,
"欠": 560,
"次": 780,
"歡": 718,
"步": 248,
"每": 260,
"比": 606,
"毫": 240,
"氣": 783,
"水": 285,
"永": 195,
"求": 245,
"池": 710,
"沒": 622,
"沙": 719,
"法": 337,
"波": 485,
"泰": 820,
"泳": 636,
"洞": 222,
"派": 449,
"海": 320,
"消": 668,
"涌": 115,
"涼": 495,
"淋": 466,
"淨": 640,
"淫": 700,
"深": 193,
"渡": 156,
"港": 386,
"游": 261,
"源": 362,
"漏": 22,
"潛": 798,
"澳": 784,
"濃": 601,
"濛": 138,
"瀝": 531,
"灣": 63,
"炆": 725,
"為": 474,
"無": 88,
"然": 383,
"煎": 309,
"照": 92,
"煲": 624,
"煽": 133,
"燒": 523,
"營": 227,
"爆": 13,
"爬": 94,
"爲": 265,
"父": 424,
"爽": 204,
"版": 823,
"牙": 377,
"牛": 210,
"物": 146,
"特": 463,
"獎": 1,
"獨": 117,
"王": 397,
"玩": 445,
"珠": 810,
"班": 562,
"現": 41,
"球": 76,
"理": 749,
"瑧": 330,
"環": 277,
"璽": 189,
"瓏": 74,
"瓦": 768,
"生": 502,
"產": 430,
"用": 753,
"田": 638,
"由": 304,
"男": 191,
"畀": 756,
"界": 576,
"畐": 73,
"留": 646,
"略": 190,
"疆": 288,
"瘀": 675,
"發": 130,
"白": 611,
"百": 787,
"的": 53,
"盒": 160,
"監": 346,
"直": 575,
"相": 306,
"省": 701,
"看": 588,
"真": 347,
"眼": 302,
"眾": 70,
"睇": 778,
"睜": 318,
"知": 458,
"石": 283,
"研": 812,
"破": 682,
"碼": 592,
"磡": 732,
"礎": 390,
"神": 584,
"票": 493,
"禮": 789,
"科": 488,
"程": 555,
"稍": 556,
"種": 574,
"稱": 16,
"積": 149,
"空": 641,
"窩": 804,
"立": 477,
"站": 111,
"竹": 247,
"笑": 301,
"等": 541,
"策": 339,
"算": 206,
"粒": 20,
"精": 472,
"糕": 365,
"系": 702,
"紀": 129,
"約": 328,
"紅": 565,
"紙": 256,
"級": 478,
"索": 324,
"累": 154,
"細": 368,
"終": 273,
"組": 505,
"結": 282,
"絡": 332,
"給": 618,
"經": 763,
"網": 403,
"緊": 534,
"總": 21,
"繼": 672,
"續": 382,
"羅": 470,
"羊": 360,
"美": 733,
"群": 83,
"義": 460,
"習": 446,
"翠": 363,
"耀": 570,
"老": 429,
"考": 43,
"者": 215,
"而": 734,
"耐": 214,
"耳": 8,
"聖": 118,
"聞": 815,
"聲": 205,
"聽": 436,
"胃": 706,
"背": 64,
"能": 249,
"脹": 462,
"腍": 686,
"腦": 42,
"腩": 119,
"腸": 621,
"膠": 52,
"膽": 182,
"臣": 770,
"自": 805,
"至": 101,
"致": 647,
"舅": 735,
"舊": 571,
"般": 435,
"色": 271,
"花": 307,
"苑": 79,
"茂": 225,
"茄": 239,
"茶": 120,
"荔": 314,
"莫": 455,
"菜": 423,
"菩": 10,
"華": 367,
"萊": 652,
"萬": 670,
"落": 35,
"著": 680,
"蓉": 351,
"蔔": 80,
"薈": 660,
"藥": 731,
"蘿": 755,
"處": 559,
"號": 294,
"蝦": 274,
"行": 145,
"街": 712,
"衛": 345,
"表": 569,
"裏": 161,
"補": 292,
"裝": 49,
"裡": 614,
"襯": 356,
"西": 620,
"要": 649,
"見": 428,
"視": 254,
"親": 32,
"覺": 348,
"角": 291,
"解": 673,
"言": 103,
"計": 136,
"討": 272,
"記": 509,
"設": 538,
"許": 236,
"訴": 290,
"評": 612,
"試": 157,
"話": 329,
"該": 107,
"認": 662,
"誕": 533,
"語": 152,
"說": 418,
"説": 142,
"請": 596,
"論": 289,
"諗": 321,
"謁": 661,
"講": 410,
"謝": 406,
"證": 355,
"識": 99,
"警": 31,
"變": 316,
"讓": 343,
"豆": 742,
"象": 359,
"豪": 518,
"豬": 751,
"貓": 674,
"貝": 797,
"財": 520,
"貪": 221,
"貴": 93,
"買": 426,
"資": 690,
"賢": 230,
"賣": 132,
"質": 405,
"賽": 30,
"贏": 372,
"走": 684,
"起": 589,
"趁": 399,
"超": 165,
"足": 528,
"跑": 126,
"路": 232,
"踢": 737,
"蹄": 116,
"身": 104,
"車": 801,
"輕": 218,
"轉": 441,
"轍": 775,
"近": 800,
"返": 379,
"迪": 109,
"退": 573,
"送": 708,
"逐": 480,
"這": 168,
"通": 599,
"逢": 258,
"進": 543,
"遇": 235,
"運": 284,
"過": 68,
"道": 512,
"達": 447,
"遠": 586,
"適": 39,
"還": 366,
"邊": 434,
"那": 211,
"郁": 631,
"部": 180,
"郵": 46,
"都": 315,
"鄉": 409,
"配": 779,
"酒": 549,
"酥": 100,
"醒": 295,
"采": 414,
"里": 547,
"重": 12,
"量": 77,
"金": 310,
"鈴": 608,
"銀": 9,
"銅": 676,
"錯": 544,
"鍾": 550,
"鏰": 659,
"鐘": 773,
"鐵": 0,
"鑫": 181,
"鑼": 335,
"長": 451,
"門": 681,
"開": 185,
"間": 705,
"關": 762,
"阻": 385,
"附": 594,
"院": 781,
"陣": 693,
"陰": 50,
"陷": 198,
"隔": 380,
"隨": 811,
"隻": 317,
"雅": 625,
"雖": 607,
"雞": 759,
"離": 51,
"難": 281,
"雪": 816,
"零": 490,
"電": 26,
"需": 802,
"靚": 524,
"非": 499,
"面": 344,
"預": 216,
"頒": 795,
"頭": 86,
"題": 175,
"願": 439,
"類": 398,
"飛": 786,
"食": 151,
"飯": 724,
"飽": 203,
"餅": 813,
"養": 656,
"餵": 275,
"香": 469,
"馬": 743,
"驗": 25,
"骨": 98,
"體": 48,
"高": 721,
"髮": 697,
"鬧": 259,
"鬼": 729,
"魔": 267,
"魚": 234,
"鮮": 278,
"鹽": 808,
"麵": 457,
"麼": 481,
"黃": 58,
"黎": 468,
"黐": 716,
"黑": 764,
"點": 551,
"黨": 370,
"鼠": 387,
"鼻": 82,
"齊": 421,
"龍": 33,
"!": 5,
",": 431,
"?": 299
}