Upload tokenizer

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "pad_token": "<pad>"
+}

tokenizer.json

@@ -0,0 +1,1808 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "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": {
+      "<bos>": 0,
+      "<eos>": 1,
+      "<pad>": 2,
+      "!": 3,
+      "\"": 4,
+      "#": 5,
+      "$": 6,
+      "%": 7,
+      "&": 8,
+      "'": 9,
+      "(": 10,
+      ")": 11,
+      "*": 12,
+      "+": 13,
+      ",": 14,
+      "-": 15,
+      ".": 16,
+      "/": 17,
+      "0": 18,
+      "1": 19,
+      "2": 20,
+      "3": 21,
+      "4": 22,
+      "5": 23,
+      "6": 24,
+      "7": 25,
+      "8": 26,
+      "9": 27,
+      ":": 28,
+      ";": 29,
+      "<": 30,
+      "=": 31,
+      ">": 32,
+      "?": 33,
+      "@": 34,
+      "A": 35,
+      "B": 36,
+      "C": 37,
+      "D": 38,
+      "E": 39,
+      "F": 40,
+      "G": 41,
+      "H": 42,
+      "I": 43,
+      "J": 44,
+      "K": 45,
+      "L": 46,
+      "M": 47,
+      "N": 48,
+      "O": 49,
+      "P": 50,
+      "Q": 51,
+      "R": 52,
+      "S": 53,
+      "T": 54,
+      "U": 55,
+      "V": 56,
+      "W": 57,
+      "X": 58,
+      "Y": 59,
+      "Z": 60,
+      "[": 61,
+      "\\": 62,
+      "]": 63,
+      "^": 64,
+      "_": 65,
+      "`": 66,
+      "a": 67,
+      "b": 68,
+      "c": 69,
+      "d": 70,
+      "e": 71,
+      "f": 72,
+      "g": 73,
+      "h": 74,
+      "i": 75,
+      "j": 76,
+      "k": 77,
+      "l": 78,
+      "m": 79,
+      "n": 80,
+      "o": 81,
+      "p": 82,
+      "q": 83,
+      "r": 84,
+      "s": 85,
+      "t": 86,
+      "u": 87,
+      "v": 88,
+      "w": 89,
+      "x": 90,
+      "y": 91,
+      "z": 92,
+      "{": 93,
+      "|": 94,
+      "}": 95,
+      "~": 96,
+      "¡": 97,
+      "¢": 98,
+      "£": 99,
+      "¤": 100,
+      "¥": 101,
+      "¦": 102,
+      "§": 103,
+      "¨": 104,
+      "©": 105,
+      "ª": 106,
+      "«": 107,
+      "¬": 108,
+      "®": 109,
+      "¯": 110,
+      "°": 111,
+      "±": 112,
+      "²": 113,
+      "³": 114,
+      "´": 115,
+      "µ": 116,
+      "¶": 117,
+      "·": 118,
+      "¸": 119,
+      "¹": 120,
+      "º": 121,
+      "»": 122,
+      "¼": 123,
+      "½": 124,
+      "¾": 125,
+      "¿": 126,
+      "À": 127,
+      "Á": 128,
+      "Â": 129,
+      "Ã": 130,
+      "Ä": 131,
+      "Å": 132,
+      "Æ": 133,
+      "Ç": 134,
+      "È": 135,
+      "É": 136,
+      "Ê": 137,
+      "Ë": 138,
+      "Ì": 139,
+      "Í": 140,
+      "Î": 141,
+      "Ï": 142,
+      "Ð": 143,
+      "Ñ": 144,
+      "Ò": 145,
+      "Ó": 146,
+      "Ô": 147,
+      "Õ": 148,
+      "Ö": 149,
+      "×": 150,
+      "Ø": 151,
+      "Ù": 152,
+      "Ú": 153,
+      "Û": 154,
+      "Ü": 155,
+      "Ý": 156,
+      "Þ": 157,
+      "ß": 158,
+      "à": 159,
+      "á": 160,
+      "â": 161,
+      "ã": 162,
+      "ä": 163,
+      "å": 164,
+      "æ": 165,
+      "ç": 166,
+      "è": 167,
+      "é": 168,
+      "ê": 169,
+      "ë": 170,
+      "ì": 171,
+      "í": 172,
+      "î": 173,
+      "ï": 174,
+      "ð": 175,
+      "ñ": 176,
+      "ò": 177,
+      "ó": 178,
+      "ô": 179,
+      "õ": 180,
+      "ö": 181,
+      "÷": 182,
+      "ø": 183,
+      "ù": 184,
+      "ú": 185,
+      "û": 186,
+      "ü": 187,
+      "ý": 188,
+      "þ": 189,
+      "ÿ": 190,
+      "Ā": 191,
+      "ā": 192,
+      "Ă": 193,
+      "ă": 194,
+      "Ą": 195,
+      "ą": 196,
+      "Ć": 197,
+      "ć": 198,
+      "Ĉ": 199,
+      "ĉ": 200,
+      "Ċ": 201,
+      "ċ": 202,
+      "Č": 203,
+      "č": 204,
+      "Ď": 205,
+      "ď": 206,
+      "Đ": 207,
+      "đ": 208,
+      "Ē": 209,
+      "ē": 210,
+      "Ĕ": 211,
+      "ĕ": 212,
+      "Ė": 213,
+      "ė": 214,
+      "Ę": 215,
+      "ę": 216,
+      "Ě": 217,
+      "ě": 218,
+      "Ĝ": 219,
+      "ĝ": 220,
+      "Ğ": 221,
+      "ğ": 222,
+      "Ġ": 223,
+      "ġ": 224,
+      "Ģ": 225,
+      "ģ": 226,
+      "Ĥ": 227,
+      "ĥ": 228,
+      "Ħ": 229,
+      "ħ": 230,
+      "Ĩ": 231,
+      "ĩ": 232,
+      "Ī": 233,
+      "ī": 234,
+      "Ĭ": 235,
+      "ĭ": 236,
+      "Į": 237,
+      "į": 238,
+      "İ": 239,
+      "ı": 240,
+      "IJ": 241,
+      "ij": 242,
+      "Ĵ": 243,
+      "ĵ": 244,
+      "Ķ": 245,
+      "ķ": 246,
+      "ĸ": 247,
+      "Ĺ": 248,
+      "ĺ": 249,
+      "Ļ": 250,
+      "ļ": 251,
+      "Ľ": 252,
+      "ľ": 253,
+      "Ŀ": 254,
+      "ŀ": 255,
+      "Ł": 256,
+      "ł": 257,
+      "Ń": 258,
+      "Ġt": 259,
+      "he": 260,
+      "Ġa": 261,
+      "Ġs": 262,
+      "Ġw": 263,
+      "nd": 264,
+      "Ġthe": 265,
+      "ed": 266,
+      "Ġb": 267,
+      "Ġto": 268,
+      "Ġand": 269,
+      "Ġh": 270,
+      "Ġf": 271,
+      "ĠT": 272,
+      "in": 273,
+      "Ġwa": 274,
+      "re": 275,
+      "it": 276,
+      "ou": 277,
+      "Ġl": 278,
+      "Ġd": 279,
+      "Ġc": 280,
+      "Ġp": 281,
+      "ay": 282,
+      "Ġm": 283,
+      "er": 284,
+      "Ġwas": 285,
+      "ĠThe": 286,
+      "om": 287,
+      "Ġhe": 288,
+      "is": 289,
+      "Ġn": 290,
+      "ar": 291,
+      "im": 292,
+      "on": 293,
+      "Ġsa": 294,
+      "id": 295,
+      "ll": 296,
+      "Ġha": 297,
+      "Ġg": 298,
+      "at": 299,
+      "ĠS": 300,
+      "ing": 301,
+      "ot": 302,
+      "en": 303,
+      "an": 304,
+      "le": 305,
+      "or": 306,
+      "ir": 307,
+      "am": 308,
+      "ĠH": 309,
+      "et": 310,
+      "Ġit": 311,
+      "Ġth": 312,
+      "ig": 313,
+      "ĠThey": 314,
+      "il": 315,
+      "Ġin": 316,
+      "Ġpl": 317,
+      "ĠHe": 318,
+      "Ġ\"": 319,
+      "ow": 320,
+      "ri": 321,
+      "ver": 322,
+      "ut": 323,
+      "Ġu": 324,
+      "Ġbe": 325,
+      "Ġplay": 326,
+      "Ġsaid": 327,
+      "ith": 328,
+      "pp": 329,
+      "Ġwith": 330,
+      "Ġday": 331,
+      "On": 332,
+      "Ġy": 333,
+      "Ġo": 334,
+      "oo": 335,
+      "ked": 336,
+      "Ġr": 337,
+      "ce": 338,
+      "ĠI": 339,
+      "Ġher": 340,
+      "ĠTim": 341,
+      "ĠShe": 342,
+      "Ġhis": 343,
+      "ld": 344,
+      "Ġst": 345,
+      "ke": 346,
+      "Ġe": 347,
+      "Ġbig": 348,
+      "nt": 349,
+      "ck": 350,
+      "Ġyou": 351,
+      "very": 352,
+      "st": 353,
+      "ve": 354,
+      "end": 355,
+      "Ġhapp": 356,
+      "Ġon": 357,
+      "un": 358,
+      "riend": 359,
+      "Ġfriend": 360,
+      "all": 361,
+      "ily": 362,
+      "ĠL": 363,
+      "Ġthey": 364,
+      "Ġnot": 365,
+      "Ġwe": 366,
+      "Ġhad": 367,
+      "Ġli": 368,
+      "Ġup": 369,
+      "Ġwant": 370,
+      "her": 371,
+      "Ġof": 372,
+      "itt": 373,
+      "ad": 374,
+      "ĠB": 375,
+      "se": 376,
+      "Ġdo": 377,
+      "Ġhappy": 378,
+      "ent": 379,
+      "Ġvery": 380,
+      "'s": 381,
+      "Ġsaw": 382,
+      "es": 383,
+      "ĠM": 384,
+      "One": 385,
+      "Ġthat": 386,
+      "ould": 387,
+      "Ġsh": 388,
+      "Ġmom": 389,
+      "Ġfor": 390,
+      "ittle": 391,
+      "Ġlittle": 392,
+      "Ġso": 393,
+      "Ġshe": 394,
+      ".\"": 395,
+      "ime": 396,
+      "ch": 397,
+      "Ġnam": 398,
+      "Ġtime": 399,
+      "Ġne": 400,
+      "Ġk": 401,
+      "ound": 402,
+      "Ġthere": 403,
+      "Ġnamed": 404,
+      "Ġbo": 405,
+      "Ġsm": 406,
+      "ĠLily": 407,
+      "Ġwere": 408,
+      "Ġwanted": 409,
+      "!\"": 410,
+      "Ġfriends": 411,
+      "Ġbut": 412,
+      "ird": 413,
+      "ĠTom": 414,
+      "out": 415,
+      "The": 416,
+      "ved": 417,
+      "ht": 418,
+      "Ġbird": 419,
+      "el": 420,
+      "Ġan": 421,
+      "al": 422,
+      "ake": 423,
+      "ĠIt": 424,
+      "Ġtoo": 425,
+      "ug": 426,
+      "ome": 427,
+      "Ġwent": 428,
+      "Ġhel": 429,
+      "ide": 430,
+      "Once": 431,
+      "Ġwh": 432,
+      "Ġhelp": 433,
+      "Ġall": 434,
+      "Ġis": 435,
+      "Ġloo": 436,
+      "ue": 437,
+      "Ġlo": 438,
+      "Ġupon": 439,
+      "ter": 440,
+      "ĠA": 441,
+      "ry": 442,
+      "ore": 443,
+      "ind": 444,
+      "Ġtoy": 445,
+      "get": 446,
+      "Ġfun": 447,
+      "ame": 448,
+      "ill": 449,
+      "Ġas": 450,
+      "Ġat": 451,
+      "Ġdid": 452,
+      "ra": 453,
+      "Ġj": 454,
+      "gether": 455,
+      "ur": 456,
+      "Ġtogether": 457,
+      "Ġre": 458,
+      "Ġse": 459,
+      "ack": 460,
+      "Ġtre": 461,
+      "Ġcat": 462,
+      "ly": 463,
+      "ood": 464,
+      "ic": 465,
+      "ted": 466,
+      "Ġcould": 467,
+      "Ġdog": 468,
+      "Ġcan": 469,
+      "ec": 470,
+      "Ġplayed": 471,
+      "ark": 472,
+      "Ġtheir": 473,
+      "ard": 474,
+      "Ġgir": 475,
+      "?\"": 476,
+      "Ġball": 477,
+      "Ġgirl": 478,
+      "Ġro": 479,
+      "way": 480,
+      "Ġhim": 481,
+      "hed": 482,
+      "Ġgo": 483,
+      "Ġle": 484,
+      "Ġfr": 485,
+      "Ġare": 486,
+      "um": 487,
+      "'t": 488,
+      "Ġout": 489,
+      "my": 490,
+      "ain": 491,
+      "Ġkn": 492,
+      "Ġsad": 493,
+      "hen": 494,
+      "ax": 495,
+      "Ġthem": 496,
+      "Ġboy": 497,
+      "Ġtree": 498,
+      "Ġman": 499,
+      "other": 500,
+      "ul": 501,
+      "Ġhave": 502,
+      "Ġcl": 503,
+      "Ġlooked": 504,
+      "Ġfound": 505,
+      "Ġloved": 506,
+      "oug": 507,
+      "Ġstar": 508,
+      "Ġsp": 509,
+      "one": 510,
+      "ĠSue": 511,
+      "hing": 512,
+      "Ġback": 513,
+      "Ġsc": 514,
+      "own": 515,
+      "ĠMax": 516,
+      "Ġlike": 517,
+      "are": 518,
+      "Ġme": 519,
+      "Ġbec": 520,
+      "side": 521,
+      "Ġcar": 522,
+      "ful": 523,
+      "ong": 524,
+      "Ġpark": 525,
+      "ight": 526,
+      "op": 527,
+      "Ġliked": 528,
+      "ĠOne": 529,
+      "elt": 530,
+      "Ġla": 531,
+      "Ġmake": 532,
+      "Ġfa": 533,
+      "Ġwould": 534,
+      "round": 535,
+      "ell": 536,
+      "You": 537,
+      "Ġfelt": 538,
+      "ĠBut": 539,
+      "omet": 540,
+      "Ġsee": 541,
+      "Ġno": 542,
+      "Ġnew": 543,
+      "ĠBen": 544,
+      "ĠW": 545,
+      "ared": 546,
+      "Ġasked": 547,
+      "Ġcame": 548,
+      "Ġstarted": 549,
+      "ag": 550,
+      "Ġother": 551,
+      "ice": 552,
+      "ĠSam": 553,
+      "ouse": 554,
+      "Ġal": 555,
+      "ought": 556,
+      "iled": 557,
+      "Ġgood": 558,
+      "Ġsomet": 559,
+      "Ġag": 560,
+      "Ġsmall": 561,
+      "ss": 562,
+      "ade": 563,
+      "Ġbr": 564,
+      "ried": 565,
+      "Ġsmiled": 566,
+      "ob": 567,
+      "Ġsay": 568,
+      "ings": 569,
+      "pot": 570,
+      "Ġfind": 571,
+      "Ġaway": 572,
+      "ty": 573,
+      "Ġmade": 574,
+      "Ġwor": 575,
+      "Ġsomething": 576,
+      "Ġex": 577,
+      "Ġput": 578,
+      "ia": 579,
+      "Ġhome": 580,
+      "ened": 581,
+      "Ġthought": 582,
+      "Ġwhat": 583,
+      "Ġfrom": 584,
+      "Ġco": 585,
+      "Ġplaying": 586,
+      "Ġmu": 587,
+      "Ġevery": 588,
+      "Ġwal": 589,
+      "ach": 590,
+      "uc": 591,
+      "arn": 592,
+      "ook": 593,
+      "ĠSpot": 594,
+      "Ġran": 595,
+      "ie": 596,
+      "ile": 597,
+      "Ġagain": 598,
+      "Ġfl": 599,
+      "ĠF": 600,
+      "Ġlaug": 601,
+      "Ġdown": 602,
+      "Ġhouse": 603,
+      "Ġtoys": 604,
+      "ave": 605,
+      "Ġscared": 606,
+      "dd": 607,
+      "Ġsome": 608,
+      "king": 609,
+      "Ġtook": 610,
+      "Ġpr": 611,
+      "ĠJ": 612,
+      "ure": 613,
+      "Ġlearn": 614,
+      "ĠYou": 615,
+      "ep": 616,
+      "Ġwill": 617,
+      "ret": 618,
+      "ny": 619,
+      "Ġbox": 620,
+      "Ġmy": 621,
+      "ab": 622,
+      "if": 623,
+      "ick": 624,
+      "Ġthings": 625,
+      "Ġyour": 626,
+      "oud": 627,
+      "Ġlived": 628,
+      "uck": 629,
+      "Ġbl": 630,
+      "Ġaround": 631,
+      "ish": 632,
+      "us": 633,
+      "Ġsun": 634,
+      ",\"": 635,
+      "Ġwhen": 636,
+      "Ġsw": 637,
+      "Ġthen": 638,
+      "Ġfe": 639,
+      "as": 640,
+      "pped": 641,
+      "ump": 642,
+      "Ġch": 643,
+      "Ġab": 644,
+      "ank": 645,
+      "ucy": 646,
+      "ĠMia": 647,
+      "Tim": 648,
+      "Th": 649,
+      "ist": 650,
+      "Ġlot": 651,
+      "oth": 652,
+      "Ġtried": 653,
+      "Ġget": 654,
+      "Ġgot": 655,
+      "Ġsays": 656,
+      "Ġknow": 657,
+      "ited": 658,
+      "ap": 659,
+      "Ġmany": 660,
+      "Ġkne": 661,
+      "Ġwho": 662,
+      "ust": 663,
+      "Ġint": 664,
+      "nder": 665,
+      "Ġdec": 666,
+      "Lily": 667,
+      "Ġpret": 668,
+      "Ġabout": 669,
+      "Ġany": 670,
+      "ĠD": 671,
+      "Ġred": 672,
+      "ous": 673,
+      "ive": 674,
+      "Ġmore": 675,
+      "Ġknew": 676,
+      "au": 677,
+      "ace": 678,
+      "ise": 679,
+      "ally": 680,
+      "Ġwater": 681,
+      "Ġcare": 682,
+      "Ġbecame": 683,
+      "Ġpic": 684,
+      "ĠLucy": 685,
+      "Ġpo": 686,
+      "ways": 687,
+      "ause": 688,
+      "fter": 689,
+      "Ġhug": 690,
+      "Ġlearned": 691,
+      "Ġalways": 692,
+      "Ġbest": 693,
+      "ĠBob": 694,
+      "Ġgre": 695,
+      "qu": 696,
+      "Ġlaughed": 697,
+      "Ġun": 698,
+      "Ġdecid": 699,
+      "urp": 700,
+      "Ġroom": 701,
+      "Ġop": 702,
+      "Ġv": 703,
+      "Ġdecided": 704,
+      "Ġho": 705,
+      "Ġbecause": 706,
+      "ĠSo": 707,
+      "Ġlook": 708,
+      "Ġpe": 709,
+      "Ġexc": 710,
+      "Ġinto": 711,
+      "Ġoutside": 712,
+      "Ġjump": 713,
+      "fe": 714,
+      "Ġboth": 715,
+      "Ġshow": 716,
+      "ant": 717,
+      "Ġeat": 718,
+      "ĠAnd": 719,
+      "ite": 720,
+      "ĠMom": 721,
+      "ers": 722,
+      "They": 723,
+      "Ġke": 724,
+      "Ġdad": 725,
+      "Ġone": 726,
+      "Ġnice": 727,
+      "udd": 728,
+      "Ġlong": 729,
+      "Tom": 730,
+      "Ġfast": 731,
+      "Ġthis": 732,
+      "Yes": 733,
+      "Ġrun": 734,
+      "ĠE": 735,
+      "Ġfeel": 736,
+      "Ġexcited": 737,
+      "nn": 738,
+      "Ġtr": 739,
+      "Ġam": 740,
+      "iny": 741,
+      "Ġtold": 742,
+      "Ġpretty": 743,
+      "ull": 744,
+      "urpr": 745,
+      "Ġsk": 746,
+      "Ġinside": 747,
+      "Ġmo": 748,
+      "Ġsurpr": 749,
+      "Ġsor": 750,
+      "our": 751,
+      "ink": 752,
+      "og": 753,
+      "Ġrock": 754,
+      "Ġtake": 755,
+      "ara": 756,
+      "Ġeach": 757,
+      "Ġmuch": 758,
+      "Wh": 759,
+      "Ġtow": 760,
+      "Ġsl": 761,
+      "lew": 762,
+      "Ġhow": 763,
+      "Ġgra": 764,
+      "Ġgave": 765,
+      "Ġstr": 766,
+      "imal": 767,
+      "But": 768,
+      "Ġanimal": 769,
+      "Ġneed": 770,
+      "Ġthan": 771,
+      "ged": 772,
+      "nna": 773,
+      "etter": 774,
+      "ĠC": 775,
+      "ven": 776,
+      "Ġunder": 777,
+      "Ġsorry": 778,
+      "ess": 779,
+      "Ġor": 780,
+      "Ġold": 781,
+      "ro": 782,
+      "urt": 783,
+      "Ġclo": 784,
+      "ised": 785,
+      "ge": 786,
+      "Ġfish": 787,
+      "Ġwalked": 788,
+      "Ġbear": 789,
+      "Ġcle": 790,
+      "ft": 791,
+      "Ġkind": 792,
+      "urn": 793,
+      "ast": 794,
+      "ase": 795,
+      "ĠHis": 796,
+      "Ġflow": 797,
+      "Ġhig": 798,
+      "Ġhappened": 799,
+      "Ġhand": 800,
+      "Ġte": 801,
+      "and": 802,
+      "Ġfood": 803,
+      "ving": 804,
+      "here": 805,
+      "Ġwat": 806,
+      "ine": 807,
+      "ĠWe": 808,
+      "Ġbug": 809,
+      "Ġlist": 810,
+      "Ġjust": 811,
+      "Ġide": 812,
+      "Ġsn": 813,
+      "Ġtry": 814,
+      "Ġanimals": 815,
+      "Ġnear": 816,
+      "gry": 817,
+      "Ġits": 818,
+      "Ġsky": 819,
+      "Ġdidn": 820,
+      "Ġidea": 821,
+      "ched": 822,
+      "pl": 823,
+      "rom": 824,
+      "Ġus": 825,
+      "Ġfi": 826,
+      "pec": 827,
+      "Ġbetter": 828,
+      "Ġshare": 829,
+      "ex": 830,
+      "Ġheard": 831,
+      "able": 832,
+      "ĠAmy": 833,
+      "Ġtw": 834,
+      "Ġen": 835,
+      "Ġlet": 836,
+      "more": 837,
+      "Ġfly": 838,
+      "Ġanymore": 839,
+      "ate": 840,
+      "Thank": 841,
+      "ff": 842,
+      "Ġflew": 843,
+      "Ġif": 844,
+      "Ġcareful": 845,
+      "Mom": 846,
+      "ĠTh": 847,
+      "ial": 848,
+      "Ġcom": 849,
+      "Ġbu": 850,
+      "lf": 851,
+      "Ġstor": 852,
+      "Ġspec": 853,
+      "Ġspecial": 854,
+      "ople": 855,
+      "ion": 856,
+      "Ġby": 857,
+      "Ġnever": 858,
+      "Ġlots": 859,
+      "Ġdan": 860,
+      "Ġlove": 861,
+      "ream": 862,
+      "Ġwind": 863,
+      "ort": 864,
+      "Ġshiny": 865,
+      "Ġfo": 866,
+      "Ġclean": 867,
+      "Ġtal": 868,
+      "ĠThen": 869,
+      "Ġend": 870,
+      "Ġmag": 871,
+      "bb": 872,
+      "Ġdon": 873,
+      "Ġgr": 874,
+      "Ġfore": 875,
+      "ak": 876,
+      "Ġpeople": 877,
+      "Ġeven": 878,
+      "Ġhard": 879,
+      "rm": 880,
+      "Ġover": 881,
+      "Ġhigh": 882,
+      "udden": 883,
+      "Ġturn": 884,
+      "Ġsafe": 885,
+      "pected": 886,
+      "Ġbad": 887,
+      "imb": 888,
+      "Ġcu": 889,
+      "Ġcake": 890,
+      "Ġcol": 891,
+      "Ġhurt": 892,
+      "Ġclimb": 893,
+      "Ġafter": 894,
+      "Ġfam": 895,
+      "Ġloud": 896,
+      "expected": 897,
+      "Ġunexpected": 898,
+      "ĠEvery": 899,
+      "Ġsurprised": 900,
+      "uddenly": 901,
+      "Ġground": 902,
+      "Let": 903,
+      "Ġbook": 904,
+      "Ġim": 905,
+      "ber": 906,
+      "ĠSara": 907,
+      "Ġpicked": 908,
+      "ail": 909,
+      "ild": 910,
+      "Ġgl": 911,
+      "Ġdoor": 912,
+      "Ġopened": 913,
+      "Ġcome": 914,
+      "Ġproud": 915,
+      "As": 916,
+      "ĠAnna": 917,
+      "arden": 918,
+      "Ġgarden": 919,
+      "ĠK": 920,
+      "Ġche": 921,
+      "ady": 922,
+      "'m": 923,
+      "Ġthanked": 924,
+      "Ġgive": 925,
+      "Ġfar": 926,
+      "Ġstill": 927,
+      "No": 928,
+      "Ġblue": 929,
+      "ip": 930,
+      "Ġcall": 931,
+      "Ġway": 932,
+      "Ġever": 933,
+      "Ġcolor": 934,
+      "ĠFrom": 935,
+      "Ġhugged": 936,
+      "Ġjumped": 937,
+      "Ġoff": 938,
+      "ĠHer": 939,
+      "iz": 940,
+      "Ġmagic": 941,
+      "ummy": 942,
+      "itty": 943,
+      "ĠWhen": 944,
+      "Ġshould": 945,
+      "ough": 946,
+      "Ġplace": 947,
+      "age": 948,
+      "Ġkid": 949,
+      "ool": 950,
+      "Ġfamily": 951,
+      "ĠIn": 952,
+      "Ġpar": 953,
+      "em": 954,
+      "Ġsmile": 955,
+      "kay": 956,
+      "ct": 957,
+      "Ġgreat": 958,
+      "Ġnow": 959,
+      "Ġwalk": 960,
+      "Ġunt": 961,
+      "uff": 962,
+      "hes": 963,
+      "Ġforest": 964,
+      "Ġstrong": 965,
+      "ĠP": 966,
+      "Ġstay": 967,
+      "Ġboat": 968,
+      "ane": 969,
+      "ture": 970,
+      "Ġqu": 971,
+      "Ġfrog": 972,
+      "Ġuntil": 973,
+      "Ġsto": 974,
+      "lease": 975,
+      "Ġdra": 976,
+      "Ġbra": 977,
+      "Ġhappily": 978,
+      "Ġbro": 979,
+      "dy": 980,
+      "oon": 981,
+      "les": 982,
+      "xt": 983,
+      "Ġnext": 984,
+      "aut": 985,
+      "Ġapp": 986,
+      "Ġhelped": 987,
+      "Ġimp": 988,
+      "Ġstick": 989,
+      "ress": 990,
+      "Ġtown": 991,
+      "Ġclos": 992,
+      "ning": 993,
+      "Ġlisten": 994,
+      "Ġbeaut": 995,
+      "Ġkids": 996,
+      "aking": 997,
+      "Ġsqu": 998,
+      "Ġbeing": 999
+    },
+    "merges": [
+      "Ġ t",
+      "h e",
+      "Ġ a",
+      "Ġ s",
+      "Ġ w",
+      "n d",
+      "Ġt he",
+      "e d",
+      "Ġ b",
+      "Ġt o",
+      "Ġa nd",
+      "Ġ h",
+      "Ġ f",
+      "Ġ T",
+      "i n",
+      "Ġw a",
+      "r e",
+      "i t",
+      "o u",
+      "Ġ l",
+      "Ġ d",
+      "Ġ c",
+      "Ġ p",
+      "a y",
+      "Ġ m",
+      "e r",
+      "Ġwa s",
+      "ĠT he",
+      "o m",
+      "Ġ he",
+      "i s",
+      "Ġ n",
+      "a r",
+      "i m",
+      "o n",
+      "Ġs a",
+      "i d",
+      "l l",
+      "Ġh a",
+      "Ġ g",
+      "a t",
+      "Ġ S",
+      "in g",
+      "o t",
+      "e n",
+      "a n",
+      "l e",
+      "o r",
+      "i r",
+      "a m",
+      "Ġ H",
+      "e t",
+      "Ġ it",
+      "Ġt h",
+      "i g",
+      "ĠThe y",
+      "i l",
+      "Ġ in",
+      "Ġp l",
+      "ĠH e",
+      "Ġ \"",
+      "o w",
+      "r i",
+      "v er",
+      "u t",
+      "Ġ u",
+      "Ġb e",
+      "Ġpl ay",
+      "Ġsa id",
+      "it h",
+      "p p",
+      "Ġw ith",
+      "Ġd ay",
+      "O n",
+      "Ġ y",
+      "Ġ o",
+      "o o",
+      "k ed",
+      "Ġ r",
+      "c e",
+      "Ġ I",
+      "Ġhe r",
+      "ĠT im",
+      "ĠS he",
+      "Ġh is",
+      "l d",
+      "Ġs t",
+      "k e",
+      "Ġ e",
+      "Ġb ig",
+      "n t",
+      "c k",
+      "Ġy ou",
+      "ver y",
+      "s t",
+      "v e",
+      "e nd",
+      "Ġha pp",
+      "Ġ on",
+      "u n",
+      "ri end",
+      "Ġf riend",
+      "a ll",
+      "il y",
+      "Ġ L",
+      "Ġthe y",
+      "Ġn ot",
+      "Ġw e",
+      "Ġha d",
+      "Ġl i",
+      "Ġu p",
+      "Ġwa nt",
+      "he r",
+      "Ġo f",
+      "it t",
+      "a d",
+      "Ġ B",
+      "s e",
+      "Ġd o",
+      "Ġhapp y",
+      "en t",
+      "Ġ very",
+      "' s",
+      "Ġsa w",
+      "e s",
+      "Ġ M",
+      "On e",
+      "Ġth at",
+      "ou ld",
+      "Ġs h",
+      "Ġm om",
+      "Ġf or",
+      "itt le",
+      "Ġl ittle",
+      "Ġs o",
+      "Ġs he",
+      ". \"",
+      "im e",
+      "c h",
+      "Ġn am",
+      "Ġt ime",
+      "Ġn e",
+      "Ġ k",
+      "ou nd",
+      "Ġthe re",
+      "Ġnam ed",
+      "Ġb o",
+      "Ġs m",
+      "ĠL ily",
+      "Ġwe re",
+      "Ġwant ed",
+      "! \"",
+      "Ġfriend s",
+      "Ġb ut",
+      "ir d",
+      "ĠT om",
+      "ou t",
+      "T he",
+      "v ed",
+      "h t",
+      "Ġb ird",
+      "e l",
+      "Ġa n",
+      "a l",
+      "a ke",
+      "ĠI t",
+      "Ġto o",
+      "u g",
+      "om e",
+      "Ġw ent",
+      "Ġhe l",
+      "id e",
+      "On ce",
+      "Ġw h",
+      "Ġhel p",
+      "Ġa ll",
+      "Ġ is",
+      "Ġl oo",
+      "u e",
+      "Ġl o",
+      "Ġup on",
+      "t er",
+      "Ġ A",
+      "r y",
+      "o re",
+      "i nd",
+      "Ġto y",
+      "g et",
+      "Ġf un",
+      "am e",
+      "i ll",
+      "Ġa s",
+      "Ġa t",
+      "Ġd id",
+      "r a",
+      "Ġ j",
+      "get her",
+      "u r",
+      "Ġto gether",
+      "Ġ re",
+      "Ġs e",
+      "a ck",
+      "Ġt re",
+      "Ġc at",
+      "l y",
+      "oo d",
+      "i c",
+      "t ed",
+      "Ġc ould",
+      "Ġdo g",
+      "Ġc an",
+      "e c",
+      "Ġplay ed",
+      "ar k",
+      "Ġthe ir",
+      "ar d",
+      "Ġg ir",
+      "? \"",
+      "Ġb all",
+      "Ġgir l",
+      "Ġr o",
+      "w ay",
+      "Ġh im",
+      "he d",
+      "Ġg o",
+      "Ġl e",
+      "Ġf r",
+      "Ġa re",
+      "u m",
+      "' t",
+      "Ġ out",
+      "m y",
+      "a in",
+      "Ġk n",
+      "Ġsa d",
+      "he n",
+      "a x",
+      "Ġthe m",
+      "Ġbo y",
+      "Ġtre e",
+      "Ġm an",
+      "ot her",
+      "u l",
+      "Ġha ve",
+      "Ġc l",
+      "Ġloo ked",
+      "Ġf ound",
+      "Ġlo ved",
+      "ou g",
+      "Ġst ar",
+      "Ġs p",
+      "on e",
+      "ĠS ue",
+      "h ing",
+      "Ġb ack",
+      "Ġs c",
+      "ow n",
+      "ĠM ax",
+      "Ġli ke",
+      "a re",
+      "Ġm e",
+      "Ġbe c",
+      "s ide",
+      "Ġc ar",
+      "f ul",
+      "on g",
+      "Ġp ark",
+      "ig ht",
+      "o p",
+      "Ġli ked",
+      "Ġ One",
+      "el t",
+      "Ġl a",
+      "Ġm ake",
+      "Ġf a",
+      "Ġw ould",
+      "r ound",
+      "e ll",
+      "Y ou",
+      "Ġf elt",
+      "ĠB ut",
+      "om et",
+      "Ġse e",
+      "Ġn o",
+      "Ġne w",
+      "ĠB en",
+      "Ġ W",
+      "ar ed",
+      "Ġas ked",
+      "Ġc ame",
+      "Ġstar ted",
+      "a g",
+      "Ġ other",
+      "i ce",
+      "ĠS am",
+      "ou se",
+      "Ġa l",
+      "oug ht",
+      "il ed",
+      "Ġg ood",
+      "Ġs omet",
+      "Ġa g",
+      "Ġsm all",
+      "s s",
+      "ad e",
+      "Ġb r",
+      "ri ed",
+      "Ġsm iled",
+      "o b",
+      "Ġs ay",
+      "ing s",
+      "p ot",
+      "Ġf ind",
+      "Ġa way",
+      "t y",
+      "Ġm ade",
+      "Ġw or",
+      "Ġsomet hing",
+      "Ġe x",
+      "Ġp ut",
+      "i a",
+      "Ġh ome",
+      "en ed",
+      "Ġth ought",
+      "Ġwh at",
+      "Ġfr om",
+      "Ġc o",
+      "Ġplay ing",
+      "Ġm u",
+      "Ġe very",
+      "Ġwa l",
+      "a ch",
+      "u c",
+      "ar n",
+      "oo k",
+      "ĠS pot",
+      "Ġr an",
+      "i e",
+      "i le",
+      "Ġag ain",
+      "Ġf l",
+      "Ġ F",
+      "Ġla ug",
+      "Ġd own",
+      "Ġh ouse",
+      "Ġtoy s",
+      "a ve",
+      "Ġsc ared",
+      "d d",
+      "Ġs ome",
+      "k ing",
+      "Ġtoo k",
+      "Ġp r",
+      "Ġ J",
+      "u re",
+      "Ġle arn",
+      "Ġ You",
+      "e p",
+      "Ġw ill",
+      "re t",
+      "n y",
+      "Ġbo x",
+      "Ġm y",
+      "a b",
+      "i f",
+      "i ck",
+      "Ġth ings",
+      "Ġyou r",
+      "ou d",
+      "Ġli ved",
+      "u ck",
+      "Ġb l",
+      "Ġa round",
+      "is h",
+      "u s",
+      "Ġs un",
+      ", \"",
+      "Ġw hen",
+      "Ġs w",
+      "Ġthe n",
+      "Ġf e",
+      "a s",
+      "pp ed",
+      "um p",
+      "Ġc h",
+      "Ġa b",
+      "an k",
+      "uc y",
+      "ĠM ia",
+      "T im",
+      "T h",
+      "is t",
+      "Ġl ot",
+      "ot h",
+      "Ġt ried",
+      "Ġg et",
+      "Ġg ot",
+      "Ġsay s",
+      "Ġkn ow",
+      "it ed",
+      "a p",
+      "Ġman y",
+      "Ġkn e",
+      "Ġwh o",
+      "u st",
+      "Ġin t",
+      "nd er",
+      "Ġd ec",
+      "L ily",
+      "Ġp ret",
+      "Ġab out",
+      "Ġan y",
+      "Ġ D",
+      "Ġr ed",
+      "ou s",
+      "i ve",
+      "Ġm ore",
+      "Ġkne w",
+      "a u",
+      "a ce",
+      "is e",
+      "all y",
+      "Ġwa ter",
+      "Ġc are",
+      "Ġbec ame",
+      "Ġp ic",
+      "ĠL ucy",
+      "Ġp o",
+      "way s",
+      "au se",
+      "f ter",
+      "Ġh ug",
+      "Ġlearn ed",
+      "Ġal ways",
+      "Ġbe st",
+      "ĠB ob",
+      "Ġg re",
+      "q u",
+      "Ġlaug hed",
+      "Ġu n",
+      "Ġdec id",
+      "ur p",
+      "Ġro om",
+      "Ġo p",
+      "Ġ v",
+      "Ġdecid ed",
+      "Ġh o",
+      "Ġbec ause",
+      "ĠS o",
+      "Ġloo k",
+      "Ġp e",
+      "Ġex c",
+      "Ġint o",
+      "Ġout side",
+      "Ġj ump",
+      "f e",
+      "Ġb oth",
+      "Ġsh ow",
+      "an t",
+      "Ġe at",
+      "ĠA nd",
+      "it e",
+      "ĠM om",
+      "er s",
+      "The y",
+      "Ġ ke",
+      "Ġd ad",
+      "Ġon e",
+      "Ġn ice",
+      "u dd",
+      "Ġl ong",
+      "T om",
+      "Ġfa st",
+      "Ġth is",
+      "Y es",
+      "Ġr un",
+      "Ġ E",
+      "Ġfe el",
+      "Ġexc ited",
+      "n n",
+      "Ġt r",
+      "Ġa m",
+      "in y",
+      "Ġto ld",
+      "Ġpret ty",
+      "u ll",
+      "urp r",
+      "Ġs k",
+      "Ġin side",
+      "Ġm o",
+      "Ġs urpr",
+      "Ġs or",
+      "ou r",
+      "in k",
+      "o g",
+      "Ġro ck",
+      "Ġt ake",
+      "ar a",
+      "Ġe ach",
+      "Ġmu ch",
+      "W h",
+      "Ġto w",
+      "Ġs l",
+      "le w",
+      "Ġh ow",
+      "Ġg ra",
+      "Ġg ave",
+      "Ġst r",
+      "im al",
+      "B ut",
+      "Ġan imal",
+      "Ġne ed",
+      "Ġth an",
+      "g ed",
+      "nn a",
+      "et ter",
+      "Ġ C",
+      "v en",
+      "Ġu nder",
+      "Ġsor ry",
+      "es s",
+      "Ġ or",
+      "Ġo ld",
+      "r o",
+      "ur t",
+      "Ġcl o",
+      "is ed",
+      "g e",
+      "Ġf ish",
+      "Ġwal ked",
+      "Ġbe ar",
+      "Ġc le",
+      "f t",
+      "Ġk ind",
+      "ur n",
+      "a st",
+      "a se",
+      "ĠH is",
+      "Ġfl ow",
+      "Ġh ig",
+      "Ġhapp ened",
+      "Ġha nd",
+      "Ġt e",
+      "a nd",
+      "Ġf ood",
+      "v ing",
+      "he re",
+      "Ġwa t",
+      "in e",
+      "ĠW e",
+      "Ġb ug",
+      "Ġl ist",
+      "Ġj ust",
+      "Ġ ide",
+      "Ġs n",
+      "Ġt ry",
+      "Ġanimal s",
+      "Ġne ar",
+      "g ry",
+      "Ġit s",
+      "Ġsk y",
+      "Ġdid n",
+      "Ġide a",
+      "c hed",
+      "p l",
+      "r om",
+      "Ġu s",
+      "Ġf i",
+      "p ec",
+      "Ġb etter",
+      "Ġsh are",
+      "e x",
+      "Ġhe ard",
+      "ab le",
+      "ĠA my",
+      "Ġt w",
+      "Ġ en",
+      "Ġl et",
+      "m ore",
+      "Ġf ly",
+      "Ġany more",
+      "at e",
+      "Th ank",
+      "f f",
+      "Ġf lew",
+      "Ġ if",
+      "Ġcare ful",
+      "M om",
+      "ĠT h",
+      "i al",
+      "Ġc om",
+      "Ġb u",
+      "l f",
+      "Ġst or",
+      "Ġsp ec",
+      "Ġspec ial",
+      "op le",
+      "i on",
+      "Ġb y",
+      "Ġne ver",
+      "Ġlot s",
+      "Ġd an",
+      "Ġlo ve",
+      "re am",
+      "Ġw ind",
+      "or t",
+      "Ġsh iny",
+      "Ġf o",
+      "Ġcle an",
+      "Ġt al",
+      "ĠThe n",
+      "Ġe nd",
+      "Ġm ag",
+      "b b",
+      "Ġd on",
+      "Ġg r",
+      "Ġf ore",
+      "a k",
+      "Ġpe ople",
+      "Ġe ven",
+      "Ġh ard",
+      "r m",
+      "Ġo ver",
+      "Ġhig h",
+      "udd en",
+      "Ġt urn",
+      "Ġsa fe",
+      "pec ted",
+      "Ġb ad",
+      "im b",
+      "Ġc u",
+      "Ġc ake",
+      "Ġco l",
+      "Ġh urt",
+      "Ġcl imb",
+      "Ġa fter",
+      "Ġf am",
+      "Ġl oud",
+      "ex pected",
+      "Ġun expected",
+      "ĠE very",
+      "Ġsurpr ised",
+      "udden ly",
+      "Ġg round",
+      "L et",
+      "Ġb ook",
+      "Ġ im",
+      "b er",
+      "ĠS ara",
+      "Ġpic ked",
+      "a il",
+      "il d",
+      "Ġg l",
+      "Ġdo or",
+      "Ġop ened",
+      "Ġc ome",
+      "Ġpr oud",
+      "A s",
+      "ĠA nna",
+      "ard en",
+      "Ġg arden",
+      "Ġ K",
+      "Ġc he",
+      "ad y",
+      "' m",
+      "Ġthan ked",
+      "Ġg ive",
+      "Ġf ar",
+      "Ġst ill",
+      "N o",
+      "Ġbl ue",
+      "i p",
+      "Ġc all",
+      "Ġwa y",
+      "Ġe ver",
+      "Ġcol or",
+      "ĠF rom",
+      "Ġhug ged",
+      "Ġjump ed",
+      "Ġof f",
+      "ĠH er",
+      "i z",
+      "Ġmag ic",
+      "um my",
+      "itt y",
+      "ĠW hen",
+      "Ġsh ould",
+      "oug h",
+      "Ġpl ace",
+      "ag e",
+      "Ġk id",
+      "oo l",
+      "Ġfam ily",
+      "ĠI n",
+      "Ġp ar",
+      "e m",
+      "Ġsm ile",
+      "k ay",
+      "c t",
+      "Ġgre at",
+      "Ġn ow",
+      "Ġwal k",
+      "Ġu nt",
+      "u ff",
+      "he s",
+      "Ġfore st",
+      "Ġstr ong",
+      "Ġ P",
+      "Ġst ay",
+      "Ġbo at",
+      "an e",
+      "t ure",
+      "Ġ qu",
+      "Ġfr og",
+      "Ġunt il",
+      "Ġst o",
+      "le ase",
+      "Ġd ra",
+      "Ġb ra",
+      "Ġhapp ily",
+      "Ġbr o",
+      "d y",
+      "o on",
+      "le s",
+      "x t",
+      "Ġne xt",
+      "a ut",
+      "Ġa pp",
+      "Ġhelp ed",
+      "Ġim p",
+      "Ġst ick",
+      "re ss",
+      "Ġtow n",
+      "Ġclo s",
+      "n ing",
+      "Ġlist en",
+      "Ġbe aut",
+      "Ġkid s",
+      "a king",
+      "Ġs qu",
+      "Ġbe ing"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}