Release Synapse-Guard-v1.2

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Comunidade-Synapse-BR/Synapse-Guard-v1.1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: Synapse-Guard-v1.2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Synapse-Guard-v1.2
+
+This model is a fine-tuned version of [Comunidade-Synapse-BR/Synapse-Guard-v1.1](https://huggingface.co/Comunidade-Synapse-BR/Synapse-Guard-v1.1) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+- Accuracy: 1.0
+- F1: 1.0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
+| 0.0017        | 1.0   | 2419 | 0.0000          | 1.0      | 1.0 |
+| 0.0011        | 2.0   | 4838 | 0.0000          | 1.0      | 1.0 |
+
+
+### Framework versions
+
+- Transformers 5.13.1
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac2b56d6ffd7d8445c6dcd4d11f06bc93da8bb79a7b7d08f46cd53dd2c389ec
+oid sha256:5f4a519e5a5c17d89814d3f910d8d4247858576b97838984769fad76383ce4ab
 size 21252768

tokenizer.json

@@ -0,0 +1,1867 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[SEP]",
+      "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
+    }
+  ],
+  "normalizer": {
+    "type": "BertNormalizer",
+    "clean_text": true,
+    "handle_chinese_chars": true,
+    "strip_accents": null,
+    "lowercase": true
+  },
+  "pre_tokenizer": {
+    "type": "BertPreTokenizer"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[SEP]": {
+        "id": "[SEP]",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "[SEP]"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "WordPiece",
+    "prefix": "##",
+    "cleanup": true
+  },
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[SEP]": 3,
+      "[MASK]": 4,
+      "!": 5,
+      "%": 6,
+      ",": 7,
+      "-": 8,
+      ".": 9,
+      "0": 10,
+      "1": 11,
+      "8": 12,
+      ":": 13,
+      "?": 14,
+      "a": 15,
+      "b": 16,
+      "c": 17,
+      "d": 18,
+      "e": 19,
+      "f": 20,
+      "g": 21,
+      "h": 22,
+      "i": 23,
+      "j": 24,
+      "k": 25,
+      "l": 26,
+      "m": 27,
+      "n": 28,
+      "o": 29,
+      "p": 30,
+      "q": 31,
+      "r": 32,
+      "s": 33,
+      "t": 34,
+      "u": 35,
+      "v": 36,
+      "w": 37,
+      "x": 38,
+      "y": 39,
+      "z": 40,
+      "👀": 41,
+      "👍": 42,
+      "📁": 43,
+      "🔑": 44,
+      "🔞": 45,
+      "🔥": 46,
+      "😈": 47,
+      "🚨": 48,
+      "##a": 49,
+      "##d": 50,
+      "##e": 51,
+      "##r": 52,
+      "##c": 53,
+      "##i": 54,
+      "##s": 55,
+      "##o": 56,
+      "##n": 57,
+      "##h": 58,
+      "##t": 59,
+      "##v": 60,
+      "##w": 61,
+      "##p": 62,
+      "##b": 63,
+      "##l": 64,
+      "##u": 65,
+      "##x": 66,
+      "##y": 67,
+      "##g": 68,
+      "##f": 69,
+      "##j": 70,
+      "##m": 71,
+      "##q": 72,
+      "##z": 73,
+      "##8": 74,
+      "##k": 75,
+      "##0": 76,
+      "##ar": 77,
+      "##te": 78,
+      "##er": 79,
+      "##en": 80,
+      "##do": 81,
+      "##ta": 82,
+      "de": 83,
+      "##ara": 84,
+      "##ue": 85,
+      "##os": 86,
+      "##ce": 87,
+      "para": 88,
+      "##or": 89,
+      "##on": 90,
+      "##iv": 91,
+      "es": 92,
+      "##da": 93,
+      "##om": 94,
+      "##al": 95,
+      "se": 96,
+      "##ra": 97,
+      "##is": 98,
+      "re": 99,
+      "##ma": 100,
+      "##re": 101,
+      "##ca": 102,
+      "##ia": 103,
+      "que": 104,
+      "vo": 105,
+      "voce": 106,
+      "##to": 107,
+      "##ente": 108,
+      "##nte": 109,
+      "##ss": 110,
+      "to": 111,
+      "no": 112,
+      "con": 113,
+      "##el": 114,
+      "um": 115,
+      "##ti": 116,
+      "com": 117,
+      "##ro": 118,
+      "##tu": 119,
+      "##ha": 120,
+      "##in": 121,
+      "##mente": 122,
+      "per": 123,
+      "##ap": 124,
+      "##qu": 125,
+      "ag": 126,
+      "##io": 127,
+      "##ali": 128,
+      "##mos": 129,
+      "##ado": 130,
+      "##gue": 131,
+      "ao": 132,
+      "##tal": 133,
+      "total": 134,
+      "##fi": 135,
+      "##riv": 136,
+      "in": 137,
+      "totalmente": 138,
+      "##ida": 139,
+      "##de": 140,
+      "##ul": 141,
+      "esta": 142,
+      "##ag": 143,
+      "pre": 144,
+      "##an": 145,
+      "ace": 146,
+      "acess": 147,
+      "da": 148,
+      "##se": 149,
+      "##ri": 150,
+      "##ivo": 151,
+      "##der": 152,
+      "ap": 153,
+      "su": 154,
+      "em": 155,
+      "fo": 156,
+      "cha": 157,
+      "os": 158,
+      "##vis": 159,
+      "##me": 160,
+      "res": 161,
+      "##por": 162,
+      "##rov": 163,
+      "##je": 164,
+      "gara": 165,
+      "garan": 166,
+      "ser": 167,
+      "des": 168,
+      "##cis": 169,
+      "##qui": 170,
+      "precis": 171,
+      "##ber": 172,
+      "fa": 173,
+      "foi": 174,
+      "li": 175,
+      "##un": 176,
+      "##ic": 177,
+      "##cao": 178,
+      "sem": 179,
+      "##es": 180,
+      "vali": 181,
+      "valido": 182,
+      "##ens": 183,
+      "ver": 184,
+      "na": 185,
+      "rap": 186,
+      "##tos": 187,
+      "so": 188,
+      "##ate": 189,
+      "tra": 190,
+      "##end": 191,
+      "ca": 192,
+      "po": 193,
+      "avis": 194,
+      "##gu": 195,
+      "##enda": 196,
+      "uma": 197,
+      "confi": 198,
+      "##tra": 199,
+      "todo": 200,
+      "##ac": 201,
+      "##at": 202,
+      "en": 203,
+      "##enta": 204,
+      "##ec": 205,
+      "ante": 206,
+      "antes": 207,
+      "##ver": 208,
+      "dever": 209,
+      "deveria": 210,
+      "pergu": 211,
+      "pergunte": 212,
+      "priv": 213,
+      "##ei": 214,
+      "ho": 215,
+      "hoje": 216,
+      "##so": 217,
+      "liber": 218,
+      "##pon": 219,
+      "nos": 220,
+      "nosso": 221,
+      "##dermos": 222,
+      "podermos": 223,
+      "ex": 224,
+      "##bre": 225,
+      "##go": 226,
+      "##ivel": 227,
+      "##mada": 228,
+      "chamada": 229,
+      "do": 230,
+      "inc": 231,
+      "atra": 232,
+      "confir": 233,
+      "nao": 234,
+      "##que": 235,
+      "##em": 236,
+      "reun": 237,
+      "##iao": 238,
+      "reuniao": 239,
+      "##ora": 240,
+      "##vor": 241,
+      "favor": 242,
+      "qu": 243,
+      "rapida": 244,
+      "cl": 245,
+      "##har": 246,
+      "for": 247,
+      "lin": 248,
+      "##aliz": 249,
+      "nin": 250,
+      "como": 251,
+      "pap": 252,
+      "##bate": 253,
+      "##uenta": 254,
+      "debate": 255,
+      "esse": 256,
+      "conse": 257,
+      "aguenta": 258,
+      "##guem": 259,
+      "##rivel": 260,
+      "incrivel": 261,
+      "ninguem": 262,
+      "papo": 263,
+      "consegue": 264,
+      "##cu": 265,
+      "##ne": 266,
+      "quem": 267,
+      "pend": 268,
+      "pendente": 269,
+      "##ito": 270,
+      "##men": 271,
+      "##us": 272,
+      "atu": 273,
+      "atualiz": 274,
+      "dis": 275,
+      "garanta": 276,
+      "aprov": 277,
+      "##eite": 278,
+      "aproveite": 279,
+      "comp": 280,
+      "##ai": 281,
+      "cas": 282,
+      "##amos": 283,
+      "perca": 284,
+      "##la": 285,
+      "agora": 286,
+      "##ario": 287,
+      "liberamos": 288,
+      "link": 289,
+      "##ut": 290,
+      "##acao": 291,
+      "##ulta": 292,
+      "##ando": 293,
+      "##dia": 294,
+      "por": 295,
+      "##udo": 296,
+      "atualizacao": 297,
+      "dia": 298,
+      "##ponivel": 299,
+      "disponivel": 300,
+      "sobre": 301,
+      "preciso": 302,
+      "bom": 303,
+      "##sos": 304,
+      "reag": 305,
+      "##endada": 306,
+      "atrasos": 307,
+      "confirme": 308,
+      "reagendada": 309,
+      "##pe": 310,
+      "este": 311,
+      "esp": 312,
+      "##cl": 313,
+      "excl": 314,
+      "exclus": 315,
+      "ul": 316,
+      "##tem": 317,
+      "esgo": 318,
+      "##tima": 319,
+      "acessos": 320,
+      "precisa": 321,
+      "forma": 322,
+      "ultima": 323,
+      "esgotem": 324,
+      "##icar": 325,
+      "avisar": 326,
+      "opor": 327,
+      "##nida": 328,
+      "##tunida": 329,
+      "oportunida": 330,
+      "oportunidade": 331,
+      "##tido": 332,
+      "ime": 333,
+      "imedia": 334,
+      "seu": 335,
+      "exclusivo": 336,
+      "tiv": 337,
+      "prov": 338,
+      "gra": 339,
+      "##agem": 340,
+      "##ass": 341,
+      "bo": 342,
+      "##up": 343,
+      "##eto": 344,
+      "##alhar": 345,
+      "##vel": 346,
+      "vi": 347,
+      "garantido": 348,
+      "##ula": 349,
+      "##quer": 350,
+      "acesso": 351,
+      "##va": 352,
+      "mens": 353,
+      "mensagem": 354,
+      "##ion": 355,
+      "pass": 356,
+      "ane": 357,
+      "anex": 358,
+      "equi": 359,
+      "equipe": 360,
+      "##sc": 361,
+      "##na": 362,
+      "##rar": 363,
+      "pro": 364,
+      "##mo": 365,
+      "##con": 366,
+      "##ido": 367,
+      "pe": 368,
+      "##tamente": 369,
+      "##nce": 370,
+      "insc": 371,
+      "##ritos": 372,
+      "chance": 373,
+      "traz": 374,
+      "aviso": 375,
+      "##aco": 376,
+      "##ativo": 377,
+      "privativo": 378,
+      "espaco": 379,
+      "inscritos": 380,
+      "acesse": 381,
+      "##mento": 382,
+      "im": 383,
+      "##porta": 384,
+      "##ique": 385,
+      "##ab": 386,
+      "perfi": 387,
+      "perfil": 388,
+      "clique": 389,
+      "##ica": 390,
+      "##lo": 391,
+      "##mi": 392,
+      "compl": 393,
+      "ja": 394,
+      "##ros": 395,
+      "hor": 396,
+      "estu": 397,
+      "##gon": 398,
+      "vergon": 399,
+      "vergonha": 400,
+      "##vi": 401,
+      "out": 402,
+      "outros": 403,
+      "imediato": 404,
+      "##ual": 405,
+      "ent": 406,
+      "##osta": 407,
+      "ar": 408,
+      "mar": 409,
+      "al": 410,
+      "resulta": 411,
+      "resultado": 412,
+      "estava": 413,
+      "##gre": 414,
+      "##ack": 415,
+      "##vo": 416,
+      "mai": 417,
+      "tudo": 418,
+      "##co": 419,
+      "fal": 420,
+      "segre": 421,
+      "segredo": 422,
+      "##oa": 423,
+      "novo": 424,
+      "pess": 425,
+      "tran": 426,
+      "completo": 427,
+      "gr": 428,
+      "##upo": 429,
+      "grupo": 430,
+      "mate": 431,
+      "##sa": 432,
+      "##rial": 433,
+      "##ico": 434,
+      "material": 435,
+      "casa": 436,
+      "##tica": 437,
+      "ur": 438,
+      "##gente": 439,
+      "urgente": 440,
+      "bio": 441,
+      "##teudo": 442,
+      "conteudo": 443,
+      "clicar": 444,
+      "##balhar": 445,
+      "trabalhar": 446,
+      "##gat": 447,
+      "##mio": 448,
+      "premio": 449,
+      "resgat": 450,
+      "resgatar": 451,
+      "ta": 452,
+      "##xa": 453,
+      "taxa": 454,
+      "privado": 455,
+      "bai": 456,
+      "##xar": 457,
+      "app": 458,
+      "baixar": 459,
+      "##sulta": 460,
+      "consulta": 461,
+      "agend": 462,
+      "agendar": 463,
+      "##tuito": 464,
+      "gratuito": 465,
+      "##pri": 466,
+      "supri": 467,
+      "##mentos": 468,
+      "comprar": 469,
+      "suprimentos": 470,
+      "jun": 471,
+      "me": 472,
+      "##alquer": 473,
+      "revis": 474,
+      "qualquer": 475,
+      "tiver": 476,
+      "passando": 477,
+      "juntos": 478,
+      "revisado": 479,
+      "ficar": 480,
+      "rico": 481,
+      "rapido": 482,
+      "descon": 483,
+      "desconto": 484,
+      "##dar": 485,
+      "prova": 486,
+      "estudar": 487,
+      "ass": 488,
+      "##quivo": 489,
+      "envi": 490,
+      "arquivo": 491,
+      "enviar": 492,
+      "respon": 493,
+      "mail": 494,
+      "responder": 495,
+      "##oma": 496,
+      "sua": 497,
+      "mu": 498,
+      "onte": 499,
+      "ola": 500,
+      "segue": 501,
+      "desde": 502,
+      "anexo": 503,
+      "ontem": 504,
+      "##ira": 505,
+      "aut": 506,
+      "##com": 507,
+      "##pens": 508,
+      "##lec": 509,
+      "##ceber": 510,
+      "selec": 511,
+      "recom": 512,
+      "receber": 513,
+      "##ionado": 514,
+      "##omatica": 515,
+      "automatica": 516,
+      "##pensa": 517,
+      "selecionado": 518,
+      "recompensa": 519,
+      "##cre": 520,
+      "ter": 521,
+      "##emos": 522,
+      "sema": 523,
+      "tivemos": 524,
+      "muito": 525,
+      "semana": 526,
+      "##ifi": 527,
+      "verifi": 528,
+      "verifique": 529,
+      "can": 530,
+      "canal": 531,
+      "pessoa": 532,
+      "par": 533,
+      "##tar": 534,
+      "aqui": 535,
+      "lem": 536,
+      "pu": 537,
+      "quando": 538,
+      "lembre": 539,
+      "puder": 540,
+      "##este": 541,
+      "##creto": 542,
+      "pi": 543,
+      "ate": 544,
+      "mes": 545,
+      "##ncao": 546,
+      "supor": 547,
+      "atencao": 548,
+      "mesmo": 549,
+      "suporte": 550,
+      "##arec": 551,
+      "va": 552,
+      "##ve": 553,
+      "##deo": 554,
+      "liberado": 555,
+      "video": 556,
+      "##di": 557,
+      "##bra": 558,
+      "descu": 559,
+      "descubra": 560,
+      "##inar": 561,
+      "assinar": 562,
+      "cara": 563,
+      "tom": 564,
+      "tomar": 565,
+      "fec": 566,
+      "boca": 567,
+      "fechar": 568,
+      "daqui": 569,
+      "sumi": 570,
+      "sumir": 571,
+      "##no": 572,
+      "inte": 573,
+      "##rne": 574,
+      "##aparec": 575,
+      "desaparec": 576,
+      "interne": 577,
+      "desaparecer": 578,
+      "internet": 579,
+      "ati": 580,
+      "hon": 581,
+      "##palhar": 582,
+      "##tude": 583,
+      "serve": 584,
+      "faca": 585,
+      "##estamente": 586,
+      "todos": 587,
+      "atrapalhar": 588,
+      "atitude": 589,
+      "honestamente": 590,
+      "beste": 591,
+      "falar": 592,
+      "parar": 593,
+      "besteira": 594,
+      "##quilo": 595,
+      "tranquilo": 596,
+      "##tri": 597,
+      "##orte": 598,
+      "##mado": 599,
+      "confirmado": 600,
+      "agenda": 601,
+      "agendado": 602,
+      "comporta": 603,
+      "comportamento": 604,
+      "sens": 605,
+      "sensual": 606,
+      "man": 607,
+      "entre": 608,
+      "##ur": 609,
+      "cup": 610,
+      "cupom": 611,
+      "##hb": 612,
+      "cashb": 613,
+      "cashback": 614,
+      "##fer": 615,
+      "##fa": 616,
+      "aposta": 617,
+      "bot": 618,
+      "apostas": 619,
+      "##tis": 620,
+      "gratis": 621,
+      "pix": 622,
+      "acu": 623,
+      "sorte": 624,
+      "##mul": 625,
+      "acumul": 626,
+      "sorteio": 627,
+      "acumulado": 628,
+      "##ura": 629,
+      "##fe": 630,
+      "##endo": 631,
+      "meto": 632,
+      "provado": 633,
+      "metodo": 634,
+      "zo": 635,
+      "##sta": 636,
+      "##testa": 637,
+      "detesta": 638,
+      "detestavel": 639,
+      "di": 640,
+      "vip": 641,
+      "imediatamente": 642,
+      "importa": 643,
+      "importante": 644,
+      "cafe": 645,
+      "manha": 646,
+      "du": 647,
+      "##ante": 648,
+      "##cion": 649,
+      "##pcion": 650,
+      "dece": 651,
+      "##pcionante": 652,
+      "decepcionante": 653,
+      "##uti": 654,
+      "inuti": 655,
+      "inutil": 656,
+      "zoom": 657,
+      "mis": 658,
+      "##avel": 659,
+      "##eravel": 660,
+      "miseravel": 661,
+      "##rendo": 662,
+      "horrendo": 663,
+      "as": 664,
+      "##oso": 665,
+      "##queroso": 666,
+      "asqueroso": 667,
+      "or": 668,
+      "##din": 669,
+      "ordin": 670,
+      "ordinario": 671,
+      "co": 672,
+      "##jeto": 673,
+      "projeto": 674,
+      "##digo": 675,
+      "codigo": 676,
+      "##moco": 677,
+      "almoco": 678,
+      "tar": 679,
+      "##efa": 680,
+      "tarefa": 681,
+      "lu": 682,
+      "sis": 683,
+      "##mp": 684,
+      "##tema": 685,
+      "sistema": 686,
+      "docu": 687,
+      "anexado": 688,
+      "documento": 689,
+      "##ly": 690,
+      "horario": 691,
+      "##lat": 692,
+      "##orio": 693,
+      "relat": 694,
+      "diario": 695,
+      "relatorio": 696,
+      "aula": 697,
+      "##les": 698,
+      "##gles": 699,
+      "ingles": 700,
+      "##eci": 701,
+      "##vida": 702,
+      "duvida": 703,
+      "ri": 704,
+      "bur": 705,
+      "##des": 706,
+      "vivo": 707,
+      "##as": 708,
+      "##tro": 709,
+      "##dic": 710,
+      "##eb": 711,
+      "ridic": 712,
+      "ridicula": 713,
+      "confira": 714,
+      "restri": 715,
+      "restrito": 716,
+      "##raca": 717,
+      "secreto": 718,
+      "renda": 719,
+      "marc": 720,
+      "##gar": 721,
+      "sugar": 722,
+      "##per": 723,
+      "nu": 724,
+      "nudes": 725,
+      "sab": 726,
+      "##acy": 727,
+      "privacy": 728,
+      "maria": 729,
+      "on": 730,
+      "##fan": 731,
+      "entrar": 732,
+      "##lyfan": 733,
+      "onlyfan": 734,
+      "onlyfans": 735,
+      "encon": 736,
+      "casual": 737,
+      "marcar": 738,
+      "encontro": 739,
+      "cens": 740,
+      "censura": 741,
+      "web": 742,
+      "##zer": 743,
+      "##cam": 744,
+      "fazer": 745,
+      "webcam": 746,
+      "##ib": 747,
+      "proib": 748,
+      "proibido": 749,
+      "passa": 750,
+      "ela": 751,
+      "##pei": 752,
+      "respei": 753,
+      "sabe": 754,
+      "respeitar": 755,
+      "ero": 756,
+      "##pl": 757,
+      "bab": 758,
+      "##ago": 759,
+      "##ou": 760,
+      "pack": 761,
+      "un": 762,
+      "unica": 763,
+      "mi": 764,
+      "extra": 765,
+      "pr": 766,
+      "##ocao": 767,
+      "##omocao": 768,
+      "rela": 769,
+      "##mpago": 770,
+      "promocao": 771,
+      "relampago": 772,
+      "quer": 773,
+      "vag": 774,
+      "##tada": 775,
+      "limi": 776,
+      "vaga": 777,
+      "limitada": 778,
+      "mag": 779,
+      "##mula": 780,
+      "formula": 781,
+      "magica": 782,
+      "ofer": 783,
+      "##divel": 784,
+      "imper": 785,
+      "oferta": 786,
+      "imperdivel": 787,
+      "gosta": 788,
+      "foto": 789,
+      "##dre": 790,
+      "ensa": 791,
+      "ensaio": 792,
+      "##res": 793,
+      "##tico": 794,
+      "erotico": 795,
+      "pica": 796,
+      "picante": 797,
+      "hu": 798,
+      "nova": 799,
+      "##cro": 800,
+      "escro": 801,
+      "suje": 802,
+      "escroto": 803,
+      "sujeito": 804,
+      "##menta": 805,
+      "##mano": 806,
+      "podre": 807,
+      "humano": 808,
+      "##ecil": 809,
+      "depl": 810,
+      "##oravel": 811,
+      "deploravel": 812,
+      "lou": 813,
+      "louca": 814,
+      "##tente": 815,
+      "##ompe": 816,
+      "incompe": 817,
+      "incompetente": 818,
+      "##ada": 819,
+      "falsa": 820,
+      "##jenta": 821,
+      "nojenta": 822,
+      "##imenta": 823,
+      "apimenta": 824,
+      "##ed": 825,
+      "otar": 826,
+      "otaria": 827,
+      "##pida": 828,
+      "estupida": 829,
+      "##ran": 830,
+      "burra": 831,
+      "##ena": 832,
+      "##ie": 833,
+      "##ire": 834,
+      "##pire": 835,
+      "expire": 836,
+      "ana": 837,
+      "ad": 838,
+      "##ulto": 839,
+      "adulto": 840,
+      "##dd": 841,
+      "dadd": 842,
+      "daddy": 843,
+      "si": 844,
+      "##curan": 845,
+      "procuran": 846,
+      "procurando": 847,
+      "##xo": 848,
+      "quente": 849,
+      "trans": 850,
+      "##tir": 851,
+      "##ger": 852,
+      "linger": 853,
+      "lingerie": 854,
+      "##aca": 855,
+      "##cal": 856,
+      "ot": 857,
+      "fraca": 858,
+      "fracass": 859,
+      "##ir": 860,
+      "##ilo": 861,
+      "##becil": 862,
+      "imbecil": 863,
+      "lui": 864,
+      "lixo": 865,
+      "otario": 866,
+      "verme": 867,
+      "burro": 868,
+      "10": 869,
+      "##erando": 870,
+      "discreto": 871,
+      "especi": 872,
+      "esperando": 873,
+      "babaca": 874,
+      "100": 875,
+      "especial": 876,
+      "bocal": 877,
+      "##graca": 878,
+      "desgraca": 879,
+      "desgracado": 880,
+      "id": 881,
+      "##iota": 882,
+      "idiota": 883,
+      "gab": 884,
+      "##riel": 885,
+      "gabriel": 886,
+      "ven": 887,
+      "##eta": 888,
+      "##gilo": 889,
+      "confer": 890,
+      "atualizado": 891,
+      "completa": 892,
+      "sigilo": 893,
+      "venha": 894,
+      "conferir": 895,
+      "cre": 896,
+      "##tino": 897,
+      "cretino": 898,
+      "luiz": 899,
+      "##cante": 900,
+      "##ores": 901,
+      "bas": 902,
+      "##tidores": 903,
+      "bastidores": 904,
+      "fracassed": 905,
+      "##tic": 906,
+      "joa": 907,
+      "midia": 908,
+      "##tor": 909,
+      "##ocante": 910,
+      "provocante": 911,
+      "fe": 912,
+      "ped": 913,
+      "##he": 914,
+      "baby": 915,
+      "##ol": 916,
+      "##ao": 917,
+      "##par": 918,
+      "transpar": 919,
+      "transparente": 920,
+      "fi": 921,
+      "##pre": 922,
+      "##zivel": 923,
+      "despre": 924,
+      "##gura": 925,
+      "figura": 926,
+      "desprezivel": 927,
+      "ro": 928,
+      "mass": 929,
+      "tan": 930,
+      "##trica": 931,
+      "massagem": 932,
+      "tantrica": 933,
+      "##oin": 934,
+      "pessoin": 935,
+      "pessoinha": 936,
+      "cena": 937,
+      "apimentada": 938,
+      "nocao": 939,
+      "ra": 940,
+      "joao": 941,
+      "##ias": 942,
+      "an": 943,
+      "##eira": 944,
+      "is": 945,
+      "##enas": 946,
+      "apenas": 947,
+      "maiores": 948,
+      "privada": 949,
+      "##ose": 950,
+      "##guel": 951,
+      "miguel": 952,
+      "##mar": 953,
+      "fer": 954,
+      "hen": 955,
+      "ma": 956,
+      "car": 957,
+      "vitor": 958,
+      "jul": 959,
+      "julia": 960,
+      "##ina": 961,
+      "pedro": 962,
+      "das": 963,
+      "le": 964,
+      "mo": 965,
+      "##istir": 966,
+      "assistir": 967,
+      "##th": 968,
+      "sess": 969,
+      "sessao": 970,
+      "##blo": 971,
+      "desblo": 972,
+      "##quear": 973,
+      "desbloquear": 974,
+      "garantir": 975,
+      "chamar": 976,
+      "##issa": 977,
+      "##son": 978,
+      "person": 979,
+      "##alizada": 980,
+      "pedi": 981,
+      "personalizada": 982,
+      "pedir": 983,
+      "acessar": 984,
+      "fern": 985,
+      "ir": 986,
+      "##tivel": 987,
+      "##istivel": 988,
+      "##resistivel": 989,
+      "irresistivel": 990,
+      "apimentado": 991,
+      "##isa": 992,
+      "##bu": 993,
+      "albu": 994,
+      "ous": 995,
+      "ousado": 996,
+      "ben": 997,
+      "la": 998,
+      "cam": 999,
+      "##dente": 1000,
+      "ardente": 1001,
+      "##uel": 1002,
+      "davi": 1003,
+      "br": 1004,
+      "pra": 1005,
+      "##rique": 1006,
+      "henrique": 1007,
+      "##cas": 1008,
+      "lucas": 1009,
+      "hel": 1010,
+      "##cia": 1011,
+      "##icito": 1012,
+      "expl": 1013,
+      "explicito": 1014,
+      "18": 1015,
+      "aca": 1016,
+      "sai": 1017,
+      "##bou": 1018,
+      "forno": 1019,
+      "acabou": 1020,
+      "sair": 1021,
+      "##tas": 1022,
+      "##bo": 1023,
+      "combo": 1024,
+      "fotos": 1025,
+      "##tel": 1026,
+      "##tiche": 1027,
+      "fetiche": 1028,
+      "##tina": 1029,
+      "lon": 1030,
+      "pa": 1031,
+      "longo": 1032,
+      "##ucao": 1033,
+      "resol": 1034,
+      "alta": 1035,
+      "resolucao": 1036,
+      "ale": 1037,
+      "fri": 1038,
+      "##ends": 1039,
+      "close": 1040,
+      "friends": 1041,
+      "ol": 1042,
+      "oliv": 1043,
+      "liz": 1044,
+      "feed": 1045,
+      "album": 1046,
+      "##val": 1047,
+      "##ana": 1048,
+      "ed": 1049,
+      "##ew": 1050,
+      "##ves": 1051,
+      "##uar": 1052,
+      "previ": 1053,
+      "eduar": 1054,
+      "preview": 1055,
+      "quentes": 1056,
+      "sa": 1057,
+      "cecil": 1058,
+      "cecilia": 1059,
+      "##man": 1060,
+      "##abel": 1061,
+      "isabel": 1062,
+      "##hia": 1063,
+      "sop": 1064,
+      "##ular": 1065,
+      "partic": 1066,
+      "particular": 1067,
+      "bar": 1068,
+      "camp": 1069,
+      "tel": 1070,
+      "##eg": 1071,
+      "##vias": 1072,
+      "##ram": 1073,
+      "previas": 1074,
+      "teleg": 1075,
+      "telegram": 1076,
+      "fes": 1077,
+      "festa": 1078,
+      "##ho": 1079,
+      "##vacao": 1080,
+      "gravacao": 1081,
+      "motel": 1082,
+      "secre": 1083,
+      "rotina": 1084,
+      "secreta": 1085,
+      "pos": 1086,
+      "##tura": 1087,
+      "postura": 1088,
+      "fl": 1089,
+      "mata": 1090,
+      "##ien": 1091,
+      "exper": 1092,
+      "##iencia": 1093,
+      "experiencia": 1094,
+      "fernan": 1095,
+      "##missa": 1096,
+      "transmissa": 1097,
+      "transmissao": 1098,
+      "cal": 1099,
+      "##iva": 1100,
+      "exclusiva": 1101,
+      "##nde": 1102,
+      "grande": 1103,
+      "fan": 1104,
+      "erotica": 1105,
+      "##tasia": 1106,
+      "fantasia": 1107,
+      "clara": 1108,
+      "gu": 1109,
+      "mel": 1110,
+      "##tia": 1111,
+      "sutia": 1112,
+      "##cca": 1113,
+      "lucca": 1114,
+      "##yan": 1115,
+      "fel": 1116,
+      "##ipe": 1117,
+      "laura": 1118,
+      "felipe": 1119,
+      "arth": 1120,
+      "carol": 1121,
+      "arthur": 1122,
+      "##il": 1123,
+      "the": 1124,
+      "vin": 1125,
+      "##ius": 1126,
+      "##icius": 1127,
+      "theo": 1128,
+      "vinicius": 1129,
+      "paul": 1130,
+      "##ice": 1131,
+      "isis": 1132,
+      "jose": 1133,
+      "gus": 1134,
+      "##tavo": 1135,
+      "gustavo": 1136,
+      "costa": 1137,
+      "mat": 1138,
+      "vitoria": 1139,
+      "sophia": 1140,
+      "##zo": 1141,
+      "luiza": 1142,
+      "eman": 1143,
+      "emanuel": 1144,
+      "##ton": 1145,
+      "anton": 1146,
+      "cun": 1147,
+      "cunha": 1148,
+      "dan": 1149,
+      "##cha": 1150,
+      "rocha": 1151,
+      "##uz": 1152,
+      "sil": 1153,
+      "ara": 1154,
+      "##osa": 1155,
+      "norte": 1156,
+      "caval": 1157,
+      "min": 1158,
+      "minas": 1159,
+      "verde": 1160,
+      "prata": 1161,
+      "mon": 1162,
+      "monte": 1163,
+      "oeste": 1164,
+      "flores": 1165,
+      "##ras": 1166,
+      "pedras": 1167,
+      "praia": 1168,
+      "dos": 1169,
+      "##dos": 1170,
+      "doura": 1171,
+      "dourados": 1172,
+      "serra": 1173,
+      "pv": 1174,
+      "alegre": 1175,
+      "amp": 1176,
+      "##aro": 1177,
+      "amparo": 1178,
+      "luisa": 1179,
+      "barb": 1180,
+      "sul": 1181,
+      "##ales": 1182,
+      "##nca": 1183,
+      "##los": 1184,
+      "go": 1185,
+      "##icio": 1186,
+      "benicio": 1187,
+      "goias": 1188,
+      "campo": 1189,
+      "##dri": 1190,
+      "rodri": 1191,
+      "nico": 1192,
+      "##ista": 1193,
+      "may": 1194,
+      "paulista": 1195,
+      "fernanda": 1196,
+      "isa": 1197,
+      "eduarda": 1198,
+      "##her": 1199,
+      "guil": 1200,
+      "##herme": 1201,
+      "guilherme": 1202,
+      "gal": 1203,
+      "galho": 1204,
+      "##ami": 1205,
+      "fracassado": 1206,
+      "##han": 1207,
+      "##min": 1208,
+      "ravi": 1209,
+      "fernando": 1210,
+      "caleb": 1211,
+      "##ry": 1212,
+      "agat": 1213,
+      "henry": 1214,
+      "agatha": 1215,
+      "##lena": 1216,
+      "enzo": 1217,
+      "##fael": 1218,
+      "rafael": 1219,
+      "carolina": 1220,
+      "##oisa": 1221,
+      "heloisa": 1222,
+      "pie": 1223,
+      "ga": 1224,
+      "##una": 1225,
+      "gael": 1226,
+      "th": 1227,
+      "benj": 1228,
+      "marce": 1229,
+      "alice": 1230,
+      "elo": 1231,
+      "eloa": 1232,
+      "sara": 1233,
+      "val": 1234,
+      "valen": 1235,
+      "##lla": 1236,
+      "eduardo": 1237,
+      "ota": 1238,
+      "##vio": 1239,
+      "##ardo": 1240,
+      "##ella": 1241,
+      "otavio": 1242,
+      "ay": 1243,
+      "alex": 1244,
+      "helena": 1245,
+      "##vin": 1246,
+      "olivia": 1247,
+      "##ony": 1248,
+      "anth": 1249,
+      "anthony": 1250,
+      "lor": 1251,
+      "be": 1252,
+      "liv": 1253,
+      "##riz": 1254,
+      "##atriz": 1255,
+      "beatriz": 1256,
+      "livia": 1257,
+      "##iel": 1258,
+      "daniel": 1259,
+      "porto": 1260,
+      "alves": 1261,
+      "##uj": 1262,
+      "arauj": 1263,
+      "araujo": 1264,
+      "fon": 1265,
+      "##seca": 1266,
+      "carval": 1267,
+      "fonseca": 1268,
+      "carvalho": 1269,
+      "luz": 1270,
+      "##reira": 1271,
+      "ferreira": 1272,
+      "mendo": 1273,
+      "##ques": 1274,
+      "marques": 1275,
+      "mendonca": 1276,
+      "bor": 1277,
+      "##ges": 1278,
+      "borges": 1279,
+      "ramos": 1280,
+      "campos": 1281,
+      "tei": 1282,
+      "##xeira": 1283,
+      "##meida": 1284,
+      "almeida": 1285,
+      "novais": 1286,
+      "oliveira": 1287,
+      "teixeira": 1288,
+      "##imento": 1289,
+      "nasc": 1290,
+      "nascimento": 1291,
+      "##veira": 1292,
+      "camara": 1293,
+      "silveira": 1294,
+      "mac": 1295,
+      "##arte": 1296,
+      "##hado": 1297,
+      "duarte": 1298,
+      "machado": 1299,
+      "##deira": 1300,
+      "caldeira": 1301,
+      "via": 1302,
+      "viana": 1303,
+      "sique": 1304,
+      "##nti": 1305,
+      "##gaca": 1306,
+      "##canti": 1307,
+      "fogaca": 1308,
+      "camar": 1309,
+      "cavalcanti": 1310,
+      "siqueira": 1311,
+      "camargo": 1312,
+      "cr": 1313,
+      "##celos": 1314,
+      "##oncelos": 1315,
+      "##sconcelos": 1316,
+      "vasconcelos": 1317,
+      "paz": 1318,
+      "cruz": 1319,
+      "cir": 1320,
+      "men": 1321,
+      "##ino": 1322,
+      "cirino": 1323,
+      "mendes": 1324,
+      "cos": 1325,
+      "gar": 1326,
+      "gon": 1327,
+      "rosa": 1328,
+      "##tela": 1329,
+      "##calves": 1330,
+      "costela": 1331,
+      "garcia": 1332,
+      "goncalves": 1333,
+      "sales": 1334,
+      "barros": 1335,
+      "##iano": 1336,
+      "##ssiano": 1337,
+      "cassiano": 1338,
+      "leao": 1339,
+      "fernandes": 1340,
+      "az": 1341,
+      "##eve": 1342,
+      "##zen": 1343,
+      "rezen": 1344,
+      "azeve": 1345,
+      "rezende": 1346,
+      "azevedo": 1347,
+      "gom": 1348,
+      "jes": 1349,
+      "pimenta": 1350,
+      "gomes": 1351,
+      "jesus": 1352,
+      "abre": 1353,
+      "bri": 1354,
+      "abreu": 1355,
+      "brito": 1356,
+      "pei": 1357,
+      "##aio": 1358,
+      "nogue": 1359,
+      "##mpaio": 1360,
+      "##xoto": 1361,
+      "sampaio": 1362,
+      "peixoto": 1363,
+      "nogueira": 1364,
+      "fre": 1365,
+      "##itas": 1366,
+      "souz": 1367,
+      "freitas": 1368,
+      "souza": 1369,
+      "moura": 1370,
+      "mor": 1371,
+      "pin": 1372,
+      "##ns": 1373,
+      "##tins": 1374,
+      "dias": 1375,
+      "martins": 1376,
+      "moreira": 1377,
+      "pinto": 1378,
+      "##dra": 1379,
+      "##erra": 1380,
+      "##doso": 1381,
+      "sous": 1382,
+      "castro": 1383,
+      "pires": 1384,
+      "andra": 1385,
+      "cardoso": 1386,
+      "mota": 1387,
+      "guerra": 1388,
+      "sousa": 1389,
+      "andrade": 1390,
+      "##gues": 1391,
+      "barbosa": 1392,
+      "rodrigues": 1393,
+      "cor": 1394,
+      "nun": 1395,
+      "##gro": 1396,
+      "##reia": 1397,
+      "##negro": 1398,
+      "silva": 1399,
+      "montenegro": 1400,
+      "correia": 1401,
+      "nunes": 1402,
+      "far": 1403,
+      "pac": 1404,
+      "##iro": 1405,
+      "##hec": 1406,
+      "monteiro": 1407,
+      "farias": 1408,
+      "pachec": 1409,
+      "pacheco": 1410,
+      "san": 1411,
+      "##icao": 1412,
+      "##ceicao": 1413,
+      "conceicao": 1414,
+      "aparec": 1415,
+      "vieira": 1416,
+      "santos": 1417,
+      "aparecida": 1418,
+      "cavalcante": 1419,
+      "lar": 1420,
+      "larissa": 1421,
+      "bra": 1422,
+      "mora": 1423,
+      "var": 1424,
+      "##gas": 1425,
+      "rios": 1426,
+      "brayan": 1427,
+      "moraes": 1428,
+      "vargas": 1429,
+      "##bei": 1430,
+      "pereira": 1431,
+      "lima": 1432,
+      "ribei": 1433,
+      "ribeiro": 1434,
+      "melo": 1435,
+      "ne": 1436,
+      "neves": 1437,
+      "##muel": 1438,
+      "samuel": 1439,
+      "pas": 1440,
+      "anna": 1441,
+      "pastor": 1442,
+      "##gao": 1443,
+      "##querque": 1444,
+      "novaes": 1445,
+      "albuquerque": 1446,
+      "aragao": 1447,
+      "lo": 1448,
+      "##pes": 1449,
+      "brenda": 1450,
+      "lopes": 1451,
+      "ju": 1452,
+      "juan": 1453,
+      "rael": 1454,
+      "melina": 1455,
+      "isaque": 1456,
+      "maya": 1457,
+      "##le": 1458,
+      "##cedo": 1459,
+      "esth": 1460,
+      "macedo": 1461,
+      "nicole": 1462,
+      "esther": 1463,
+      "ste": 1464,
+      "##phan": 1465,
+      "gabriela": 1466,
+      "stephan": 1467,
+      "stephany": 1468,
+      "##ine": 1469,
+      "apol": 1470,
+      "caroline": 1471,
+      "apollo": 1472,
+      "ian": 1473,
+      "kami": 1474,
+      "yas": 1475,
+      "##lly": 1476,
+      "##rico": 1477,
+      "enrico": 1478,
+      "marina": 1479,
+      "barbara": 1480,
+      "kamilly": 1481,
+      "yasmin": 1482,
+      "hei": 1483,
+      "ig": 1484,
+      "##arice": 1485,
+      "clarice": 1486,
+      "mariana": 1487,
+      "rafaela": 1488,
+      "heitor": 1489,
+      "igor": 1490,
+      "evel": 1491,
+      "##yn": 1492,
+      "emanuelly": 1493,
+      "calebe": 1494,
+      "evelyn": 1495,
+      "##talia": 1496,
+      "natalia": 1497,
+      "cami": 1498,
+      "##las": 1499,
+      "isabela": 1500,
+      "nicolas": 1501,
+      "camila": 1502,
+      "jo": 1503,
+      "##dro": 1504,
+      "##rina": 1505,
+      "##andro": 1506,
+      "sabrina": 1507,
+      "leandro": 1508,
+      "joana": 1509,
+      "dom": 1510,
+      "ester": 1511,
+      "maysa": 1512,
+      "au": 1513,
+      "##eca": 1514,
+      "##sto": 1515,
+      "##beca": 1516,
+      "rebeca": 1517,
+      "##gusto": 1518,
+      "alana": 1519,
+      "milena": 1520,
+      "lais": 1521,
+      "augusto": 1522,
+      "gio": 1523,
+      "##van": 1524,
+      "hugo": 1525,
+      "bruna": 1526,
+      "melissa": 1527,
+      "giovan": 1528,
+      "giovanna": 1529,
+      "ryan": 1530,
+      "##tim": 1531,
+      "dante": 1532,
+      "##quel": 1533,
+      "raquel": 1534,
+      "valentim": 1535,
+      "##vy": 1536,
+      "##ticia": 1537,
+      "ravy": 1538,
+      "leticia": 1539,
+      "sarah": 1540,
+      "asa": 1541,
+      "aman": 1542,
+      "##ego": 1543,
+      "diego": 1544,
+      "marcos": 1545,
+      "flor": 1546,
+      "pietra": 1547,
+      "asafe": 1548,
+      "amanda": 1549,
+      "ber": 1550,
+      "##nardo": 1551,
+      "##teo": 1552,
+      "jade": 1553,
+      "matteo": 1554,
+      "aylla": 1555,
+      "bernardo": 1556,
+      "##omas": 1557,
+      "zoe": 1558,
+      "emanuella": 1559,
+      "danilo": 1560,
+      "thomas": 1561,
+      "yu": 1562,
+      "##ah": 1563,
+      "noah": 1564,
+      "##heus": 1565,
+      "matheus": 1566,
+      "##amim": 1567,
+      "benjamim": 1568,
+      "yuri": 1569,
+      "##quim": 1570,
+      "luana": 1571,
+      "joaquim": 1572,
+      "isaac": 1573,
+      "marcela": 1574,
+      "el": 1575,
+      "rha": 1576,
+      "stel": 1577,
+      "##amin": 1578,
+      "maite": 1579,
+      "mariane": 1580,
+      "juliana": 1581,
+      "pietro": 1582,
+      "benjamin": 1583,
+      "marcelo": 1584,
+      "elisa": 1585,
+      "rhavi": 1586,
+      "stella": 1587,
+      "hada": 1588,
+      "vic": 1589,
+      "##than": 1590,
+      "##ssa": 1591,
+      "emil": 1592,
+      "nathan": 1593,
+      "luan": 1594,
+      "hellena": 1595,
+      "isabella": 1596,
+      "thales": 1597,
+      "hadassa": 1598,
+      "vicente": 1599,
+      "emilly": 1600,
+      "bella": 1601,
+      "yan": 1602,
+      "##lana": 1603,
+      "allana": 1604,
+      "fran": 1605,
+      "lara": 1606,
+      "lun": 1607,
+      "##ua": 1608,
+      "##cisco": 1609,
+      "##icia": 1610,
+      "caua": 1611,
+      "alicia": 1612,
+      "manuel": 1613,
+      "otto": 1614,
+      "isabelly": 1615,
+      "alexia": 1616,
+      "francisco": 1617,
+      "lunna": 1618,
+      "manuella": 1619,
+      "eri": 1620,
+      "##ck": 1621,
+      "raul": 1622,
+      "antonio": 1623,
+      "antonella": 1624,
+      "erick": 1625,
+      "aur": 1626,
+      "luna": 1627,
+      "##andre": 1628,
+      "rodrigo": 1629,
+      "alexandre": 1630,
+      "aurora": 1631,
+      "ke": 1632,
+      "##uno": 1633,
+      "levi": 1634,
+      "bruno": 1635,
+      "lorena": 1636,
+      "kevin": 1637,
+      "thia": 1638,
+      "##fia": 1639,
+      "##doro": 1640,
+      "##rella": 1641,
+      "sofia": 1642,
+      "caio": 1643,
+      "mateus": 1644,
+      "mirella": 1645,
+      "theodoro": 1646,
+      "thiago": 1647,
+      "##gi": 1648,
+      "luigi": 1649,
+      "carlos": 1650,
+      "bryan": 1651,
+      "oliver": 1652,
+      "antony": 1653,
+      "##adora": 1654,
+      "##rilo": 1655,
+      "murilo": 1656,
+      "isadora": 1657,
+      "lavin": 1658,
+      "valentina": 1659,
+      "lavinia": 1660,
+      "dio": 1661,
+      "##hie": 1662,
+      "##hias": 1663,
+      "##eno": 1664,
+      "##onardo": 1665,
+      "nina": 1666,
+      "leonardo": 1667,
+      "breno": 1668,
+      "sophie": 1669,
+      "mathias": 1670,
+      "diogo": 1671,
+      "ren": 1672,
+      "yago": 1673,
+      "##uela": 1674,
+      "catar": 1675,
+      "manuela": 1676,
+      "luara": 1677,
+      "mariah": 1678,
+      "eloah": 1679,
+      "ayla": 1680,
+      "renan": 1681,
+      "catarina": 1682,
+      "caue": 1683,
+      "paulo": 1684,
+      "kai": 1685,
+      "lia": 1686,
+      "andre": 1687,
+      "kaique": 1688,
+      "liam": 1689,
+      "gabrielly": 1690,
+      "bento": 1691,
+      "bia": 1692,
+      "##enzo": 1693,
+      "lorenzo": 1694,
+      "bianca": 1695,
+      "leo": 1696,
+      "daniela": 1697,
+      "jos": 1698,
+      "josue": 1699,
+      "gan": 1700,
+      "ganha": 1701,
+      "nem": 1702,
+      "tem": 1703,
+      "##po": 1704,
+      "sei": 1705,
+      "perco": 1706,
+      "tempo": 1707,
+      "vai": 1708,
+      "##via": 1709,
+      "envia": 1710,
+      "enviado": 1711
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": [
+    "[PAD]",
+    "[UNK]",
+    "[CLS]",
+    "[SEP]",
+    "[MASK]"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}