Instructions to use stage-babylm/last-hope-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stage-babylm/last-hope-tokenizer with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("stage-babylm/last-hope-tokenizer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "[UNK]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "[CLS]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "[SEP]", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "[PAD]", | |
| "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": "Lowercase" | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 1 | |
| } | |
| } | |
| ], | |
| "special_tokens": {} | |
| }, | |
| "decoder": null, | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[UNK]": 0, | |
| "[CLS]": 1, | |
| "[SEP]": 2, | |
| "[PAD]": 3, | |
| "[MASK]": 4, | |
| ".": 5, | |
| ":": 6, | |
| "-": 7, | |
| "a": 8, | |
| "about": 9, | |
| "above": 10, | |
| "acceleration": 11, | |
| "across": 12, | |
| "act": 13, | |
| "action": 14, | |
| "after": 15, | |
| "again": 16, | |
| "age": 17, | |
| "agree": 18, | |
| "air": 19, | |
| "alarm": 20, | |
| "alien": 21, | |
| "all": 22, | |
| "alone": 23, | |
| "amaze": 24, | |
| "ammonia": 25, | |
| "an": 26, | |
| "analyst": 27, | |
| "analyze": 28, | |
| "and": 29, | |
| "angle": 30, | |
| "animal": 31, | |
| "anom-a": 32, | |
| "anom-b": 33, | |
| "anom-c": 34, | |
| "anomaly": 35, | |
| "answer": 36, | |
| "ant": 37, | |
| "antarctica": 38, | |
| "antenna": 39, | |
| "apollo": 40, | |
| "appear": 41, | |
| "arc": 42, | |
| "area": 43, | |
| "argon": 44, | |
| "argue": 45, | |
| "arm": 46, | |
| "around": 47, | |
| "arrive": 48, | |
| "art": 49, | |
| "as": 50, | |
| "ask": 51, | |
| "at": 52, | |
| "atmosphere": 53, | |
| "atom": 54, | |
| "attack": 55, | |
| "automatically": 56, | |
| "avoid": 57, | |
| "away": 58, | |
| "baby": 59, | |
| "back": 60, | |
| "backwards": 61, | |
| "bacteria": 62, | |
| "bad": 63, | |
| "bag": 64, | |
| "ball": 65, | |
| "bandage": 66, | |
| "barrier": 67, | |
| "base": 68, | |
| "battery": 69, | |
| "bay": 70, | |
| "be": 71, | |
| "beat": 72, | |
| "beautiful": 73, | |
| "because": 74, | |
| "become": 75, | |
| "bed": 76, | |
| "bedroom": 77, | |
| "beetle": 78, | |
| "before": 79, | |
| "behind": 80, | |
| "believe": 81, | |
| "belt": 82, | |
| "better": 83, | |
| "between": 84, | |
| "big": 85, | |
| "biology": 86, | |
| "bird": 87, | |
| "birthday": 88, | |
| "bite": 89, | |
| "blind": 90, | |
| "block": 91, | |
| "blow": 92, | |
| "blue": 93, | |
| "body": 94, | |
| "boil": 95, | |
| "bolt": 96, | |
| "bone": 97, | |
| "book": 98, | |
| "boost": 99, | |
| "borrow": 100, | |
| "both": 101, | |
| "bottle": 102, | |
| "box": 103, | |
| "brain": 104, | |
| "brave": 105, | |
| "break": 106, | |
| "breathe": 107, | |
| "breed": 108, | |
| "bring": 109, | |
| "broken": 110, | |
| "brown": 111, | |
| "bug": 112, | |
| "build": 113, | |
| "bump": 114, | |
| "burn": 115, | |
| "bus": 116, | |
| "busy": 117, | |
| "but": 118, | |
| "button": 119, | |
| "by": 120, | |
| "cabin": 121, | |
| "cable": 122, | |
| "cake": 123, | |
| "calculate": 124, | |
| "calibration": 125, | |
| "call": 126, | |
| "calm": 127, | |
| "camera": 128, | |
| "can": 129, | |
| "candle": 130, | |
| "capacitor": 131, | |
| "capacity": 132, | |
| "car": 133, | |
| "carbon": 134, | |
| "care": 135, | |
| "cargo": 136, | |
| "cat": 137, | |
| "cause": 138, | |
| "ceiling": 139, | |
| "celebrate": 140, | |
| "cell": 141, | |
| "centrifuge": 142, | |
| "cetocite": 143, | |
| "chain": 144, | |
| "chair": 145, | |
| "change": 146, | |
| "charge": 147, | |
| "chase": 148, | |
| "check": 149, | |
| "cheer": 150, | |
| "chemical": 151, | |
| "chemistry": 152, | |
| "chicken": 153, | |
| "child": 154, | |
| "chloe": 155, | |
| "circuit": 156, | |
| "city": 157, | |
| "class": 158, | |
| "clean": 159, | |
| "clever": 160, | |
| "click": 161, | |
| "climb": 162, | |
| "clock": 163, | |
| "close": 164, | |
| "cloud": 165, | |
| "coat": 166, | |
| "cold": 167, | |
| "collapse": 168, | |
| "collector": 169, | |
| "collision": 170, | |
| "color": 171, | |
| "come": 172, | |
| "comfortable": 173, | |
| "compass": 174, | |
| "complete": 175, | |
| "computer": 176, | |
| "conflict": 177, | |
| "constant": 178, | |
| "consume": 179, | |
| "contest": 180, | |
| "continue": 181, | |
| "control": 182, | |
| "cook": 183, | |
| "cool": 184, | |
| "copy": 185, | |
| "correct": 186, | |
| "could": 187, | |
| "count": 188, | |
| "cover": 189, | |
| "crash": 190, | |
| "crazy": 191, | |
| "create": 192, | |
| "creature": 193, | |
| "crew": 194, | |
| "cross": 195, | |
| "crush": 196, | |
| "cry": 197, | |
| "cryoplast": 198, | |
| "culture": 199, | |
| "cup": 200, | |
| "cure": 201, | |
| "curious": 202, | |
| "cut": 203, | |
| "damage": 204, | |
| "dance": 205, | |
| "danger": 206, | |
| "dangerous": 207, | |
| "dark": 208, | |
| "data": 209, | |
| "day": 210, | |
| "dead": 211, | |
| "death": 212, | |
| "debate": 213, | |
| "decay": 214, | |
| "deck": 215, | |
| "deep": 216, | |
| "delay": 217, | |
| "density": 218, | |
| "design": 219, | |
| "desk": 220, | |
| "destroy": 221, | |
| "detail": 222, | |
| "dial": 223, | |
| "die": 224, | |
| "diet": 225, | |
| "difference": 226, | |
| "different": 227, | |
| "dig": 228, | |
| "digital": 229, | |
| "dim": 230, | |
| "direction": 231, | |
| "dirt": 232, | |
| "dirty": 233, | |
| "disagree": 234, | |
| "disease": 235, | |
| "distance": 236, | |
| "dizzy": 237, | |
| "do": 238, | |
| "doctor": 239, | |
| "dog": 240, | |
| "door": 241, | |
| "double": 242, | |
| "down": 243, | |
| "drag": 244, | |
| "draw": 245, | |
| "dream": 246, | |
| "drive": 247, | |
| "dry": 248, | |
| "duck": 249, | |
| "dust": 250, | |
| "each": 251, | |
| "early": 252, | |
| "earth": 253, | |
| "easy": 254, | |
| "eat": 255, | |
| "ecosystem": 256, | |
| "edge": 257, | |
| "egg": 258, | |
| "eject": 259, | |
| "electric": 260, | |
| "electronic": 261, | |
| "element": 262, | |
| "elephant": 263, | |
| "empty": 264, | |
| "end": 265, | |
| "enemy": 266, | |
| "energy": 267, | |
| "engine": 268, | |
| "engineer": 269, | |
| "english": 270, | |
| "enjoy": 271, | |
| "enough": 272, | |
| "ensure": 273, | |
| "enter": 274, | |
| "environment": 275, | |
| "equipment": 276, | |
| "error": 277, | |
| "escape": 278, | |
| "ethical": 279, | |
| "evacuate": 280, | |
| "every": 281, | |
| "everything": 282, | |
| "evolution": 283, | |
| "exercise": 284, | |
| "exist": 285, | |
| "exit": 286, | |
| "explain": 287, | |
| "explore": 288, | |
| "explosion": 289, | |
| "explosive": 290, | |
| "eye": 291, | |
| "face": 292, | |
| "fade": 293, | |
| "fail": 294, | |
| "failure": 295, | |
| "fake": 296, | |
| "fall": 297, | |
| "false": 298, | |
| "family": 299, | |
| "far": 300, | |
| "farm": 301, | |
| "fascinating": 302, | |
| "fast": 303, | |
| "fat": 304, | |
| "fault": 305, | |
| "favorite": 306, | |
| "fear": 307, | |
| "feature": 308, | |
| "feel": 309, | |
| "female": 310, | |
| "few": 311, | |
| "field": 312, | |
| "fight": 313, | |
| "fill": 314, | |
| "filter": 315, | |
| "find": 316, | |
| "finger": 317, | |
| "finish": 318, | |
| "fire": 319, | |
| "first": 320, | |
| "fish": 321, | |
| "fist": 322, | |
| "fix": 323, | |
| "float": 324, | |
| "floor": 325, | |
| "flow": 326, | |
| "fly": 327, | |
| "fog": 328, | |
| "follow": 329, | |
| "food": 330, | |
| "foot": 331, | |
| "for": 332, | |
| "force": 333, | |
| "forest": 334, | |
| "forget": 335, | |
| "form": 336, | |
| "forward": 337, | |
| "fragile": 338, | |
| "free": 339, | |
| "freeze": 340, | |
| "frequency": 341, | |
| "fresh": 342, | |
| "friend": 343, | |
| "from": 344, | |
| "front": 345, | |
| "fuel": 346, | |
| "full": 347, | |
| "fun": 348, | |
| "function": 349, | |
| "funny": 350, | |
| "fusion": 351, | |
| "future": 352, | |
| "game": 353, | |
| "games": 354, | |
| "garden": 355, | |
| "gas": 356, | |
| "generate": 357, | |
| "gift": 358, | |
| "girl": 359, | |
| "give": 360, | |
| "glass": 361, | |
| "global": 362, | |
| "glove": 363, | |
| "glow": 364, | |
| "go": 365, | |
| "goal": 366, | |
| "gold": 367, | |
| "good": 368, | |
| "gravity": 369, | |
| "great": 370, | |
| "green": 371, | |
| "greet": 372, | |
| "group": 373, | |
| "grow": 374, | |
| "growl": 375, | |
| "guide": 376, | |
| "guitar": 377, | |
| "habitat": 378, | |
| "hand": 379, | |
| "happen": 380, | |
| "happy": 381, | |
| "hard": 382, | |
| "hat": 383, | |
| "hate": 384, | |
| "have": 385, | |
| "hayes": 386, | |
| "head": 387, | |
| "heal": 388, | |
| "health": 389, | |
| "hear": 390, | |
| "heart": 391, | |
| "heat": 392, | |
| "heavy": 393, | |
| "helium": 394, | |
| "hello": 395, | |
| "helmet": 396, | |
| "help": 397, | |
| "here": 398, | |
| "hibernate": 399, | |
| "hide": 400, | |
| "high": 401, | |
| "history": 402, | |
| "hit": 403, | |
| "hold": 404, | |
| "hole": 405, | |
| "home": 406, | |
| "honor": 407, | |
| "hope": 408, | |
| "horn": 409, | |
| "horse": 410, | |
| "hot": 411, | |
| "house": 412, | |
| "how": 413, | |
| "hugo": 414, | |
| "hull": 415, | |
| "human": 416, | |
| "hurry": 417, | |
| "ice": 418, | |
| "idea": 419, | |
| "ideal": 420, | |
| "if": 421, | |
| "ignore": 422, | |
| "ill": 423, | |
| "image": 424, | |
| "imagine": 425, | |
| "in": 426, | |
| "increase": 427, | |
| "inert": 428, | |
| "injury": 429, | |
| "ink": 430, | |
| "insect": 431, | |
| "inside": 432, | |
| "inspect": 433, | |
| "intense": 434, | |
| "internet": 435, | |
| "into": 436, | |
| "intuition": 437, | |
| "it": 438, | |
| "join": 439, | |
| "joint": 440, | |
| "joke": 441, | |
| "journey": 442, | |
| "joy": 443, | |
| "jump": 444, | |
| "keep": 445, | |
| "key": 446, | |
| "kill": 447, | |
| "kitchen": 448, | |
| "knife": 449, | |
| "know": 450, | |
| "knowledge": 451, | |
| "kryon": 452, | |
| "kryonian": 453, | |
| "laboratory": 454, | |
| "lack": 455, | |
| "land": 456, | |
| "language": 457, | |
| "laser": 458, | |
| "last": 459, | |
| "late": 460, | |
| "later": 461, | |
| "laugh": 462, | |
| "launch": 463, | |
| "laundry": 464, | |
| "law": 465, | |
| "layer": 466, | |
| "lead": 467, | |
| "leader": 468, | |
| "leaf": 469, | |
| "leak": 470, | |
| "learn": 471, | |
| "learning": 472, | |
| "leave": 473, | |
| "left": 474, | |
| "lens": 475, | |
| "less": 476, | |
| "lesson": 477, | |
| "level": 478, | |
| "lever": 479, | |
| "lie": 480, | |
| "life": 481, | |
| "light": 482, | |
| "lightning": 483, | |
| "like": 484, | |
| "limit": 485, | |
| "line": 486, | |
| "lion": 487, | |
| "liquid": 488, | |
| "list": 489, | |
| "listen": 490, | |
| "live": 491, | |
| "load": 492, | |
| "lock": 493, | |
| "logic": 494, | |
| "long": 495, | |
| "look": 496, | |
| "lose": 497, | |
| "lost": 498, | |
| "loud": 499, | |
| "love": 500, | |
| "low": 501, | |
| "lower": 502, | |
| "loyal": 503, | |
| "luck": 504, | |
| "lucky": 505, | |
| "lung": 506, | |
| "machine": 507, | |
| "magnetic": 508, | |
| "maintain": 509, | |
| "maintenance": 510, | |
| "make": 511, | |
| "manual": 512, | |
| "many": 513, | |
| "map": 514, | |
| "marina": 515, | |
| "mark": 516, | |
| "mass": 517, | |
| "mate": 518, | |
| "material": 519, | |
| "math": 520, | |
| "mathieu": 521, | |
| "matter": 522, | |
| "may": 523, | |
| "meal": 524, | |
| "mean": 525, | |
| "measure": 526, | |
| "measured": 527, | |
| "mechanic": 528, | |
| "medicine": 529, | |
| "meet": 530, | |
| "melt": 531, | |
| "membrane": 532, | |
| "memory": 533, | |
| "mess": 534, | |
| "message": 535, | |
| "met": 536, | |
| "metal": 537, | |
| "meteor": 538, | |
| "methane": 539, | |
| "method": 540, | |
| "microbe": 541, | |
| "microphone": 542, | |
| "microscope": 543, | |
| "migrate": 544, | |
| "minute": 545, | |
| "mirror": 546, | |
| "miss": 547, | |
| "mistake": 548, | |
| "mix": 549, | |
| "mode": 550, | |
| "model": 551, | |
| "money": 552, | |
| "monitor": 553, | |
| "monkey": 554, | |
| "moon": 555, | |
| "moral": 556, | |
| "more": 557, | |
| "mosquito": 558, | |
| "motor": 559, | |
| "mount": 560, | |
| "mountain": 561, | |
| "mouth": 562, | |
| "move": 563, | |
| "movie": 564, | |
| "much": 565, | |
| "muscle": 566, | |
| "music": 567, | |
| "must": 568, | |
| "mutate": 569, | |
| "mutates": 570, | |
| "mutation": 571, | |
| "naked": 572, | |
| "natural": 573, | |
| "nature": 574, | |
| "nausea": 575, | |
| "near": 576, | |
| "neck": 577, | |
| "need": 578, | |
| "nerve": 579, | |
| "new": 580, | |
| "news": 581, | |
| "next": 582, | |
| "night": 583, | |
| "nitrogen": 584, | |
| "no": 585, | |
| "noe": 586, | |
| "noise": 587, | |
| "none": 588, | |
| "not": 589, | |
| "nothing": 590, | |
| "now": 591, | |
| "nuclear": 592, | |
| "nucleus": 593, | |
| "number": 594, | |
| "nutrient": 595, | |
| "object": 596, | |
| "observe": 597, | |
| "odd": 598, | |
| "of": 599, | |
| "off": 600, | |
| "okay": 601, | |
| "old": 602, | |
| "on": 603, | |
| "one": 604, | |
| "only": 605, | |
| "open": 606, | |
| "or": 607, | |
| "orbit": 608, | |
| "order": 609, | |
| "organ": 610, | |
| "other": 611, | |
| "out": 612, | |
| "outcome": 613, | |
| "outside": 614, | |
| "over": 615, | |
| "oxygen": 616, | |
| "page": 617, | |
| "pain": 618, | |
| "pan": 619, | |
| "paper": 620, | |
| "part": 621, | |
| "partner": 622, | |
| "past": 623, | |
| "path": 624, | |
| "pattern": 625, | |
| "peace": 626, | |
| "people": 627, | |
| "perfect": 628, | |
| "perfection": 629, | |
| "person": 630, | |
| "petri": 631, | |
| "philippe": 632, | |
| "photo": 633, | |
| "physics": 634, | |
| "pick": 635, | |
| "picture": 636, | |
| "piece": 637, | |
| "pill": 638, | |
| "pilot": 639, | |
| "pipe": 640, | |
| "place": 641, | |
| "plan": 642, | |
| "planet": 643, | |
| "plant": 644, | |
| "play": 645, | |
| "plot": 646, | |
| "pole": 647, | |
| "polish": 648, | |
| "population": 649, | |
| "power": 650, | |
| "praise": 651, | |
| "pray": 652, | |
| "predator": 653, | |
| "prepare": 654, | |
| "pressure": 655, | |
| "prime": 656, | |
| "probe": 657, | |
| "problem": 658, | |
| "process": 659, | |
| "product": 660, | |
| "professor": 661, | |
| "program": 662, | |
| "progress": 663, | |
| "project": 664, | |
| "protect": 665, | |
| "protein": 666, | |
| "protocol": 667, | |
| "proud": 668, | |
| "prove": 669, | |
| "provide": 670, | |
| "pull": 671, | |
| "pure": 672, | |
| "push": 673, | |
| "put": 674, | |
| "puzzle": 675, | |
| "quality": 676, | |
| "question": 677, | |
| "quiet": 678, | |
| "rabbit": 679, | |
| "radiation": 680, | |
| "rain": 681, | |
| "range": 682, | |
| "ray": 683, | |
| "reach": 684, | |
| "reaction": 685, | |
| "reactor": 686, | |
| "read": 687, | |
| "ready": 688, | |
| "real": 689, | |
| "reason": 690, | |
| "recover": 691, | |
| "recovery": 692, | |
| "recruit": 693, | |
| "red": 694, | |
| "reduce": 695, | |
| "refuse": 696, | |
| "release": 697, | |
| "remember": 698, | |
| "repair": 699, | |
| "report": 700, | |
| "reproduce": 701, | |
| "reproduction": 702, | |
| "rescue": 703, | |
| "research": 704, | |
| "researcher": 705, | |
| "resistant": 706, | |
| "resolution": 707, | |
| "resource": 708, | |
| "result": 709, | |
| "return": 710, | |
| "reuse": 711, | |
| "reward": 712, | |
| "ride": 713, | |
| "right": 714, | |
| "rise": 715, | |
| "risk": 716, | |
| "road": 717, | |
| "robot": 718, | |
| "rock": 719, | |
| "rocket": 720, | |
| "roll": 721, | |
| "ronan": 722, | |
| "room": 723, | |
| "rope": 724, | |
| "rot": 725, | |
| "rule": 726, | |
| "run": 727, | |
| "rust": 728, | |
| "sad": 729, | |
| "safe": 730, | |
| "safety": 731, | |
| "same": 732, | |
| "sample": 733, | |
| "sand": 734, | |
| "save": 735, | |
| "say": 736, | |
| "scan": 737, | |
| "scare": 738, | |
| "school": 739, | |
| "schoolteacher": 740, | |
| "science": 741, | |
| "scientist": 742, | |
| "scientists": 743, | |
| "screen": 744, | |
| "sea": 745, | |
| "seal": 746, | |
| "search": 747, | |
| "season": 748, | |
| "seat": 749, | |
| "secret": 750, | |
| "see": 751, | |
| "seek": 752, | |
| "select": 753, | |
| "self": 754, | |
| "send": 755, | |
| "sense": 756, | |
| "sensor": 757, | |
| "session": 758, | |
| "shadow": 759, | |
| "shake": 760, | |
| "shame": 761, | |
| "shape": 762, | |
| "share": 763, | |
| "shark": 764, | |
| "sharp": 765, | |
| "shelf": 766, | |
| "shell": 767, | |
| "shelter": 768, | |
| "shield": 769, | |
| "ship": 770, | |
| "shock": 771, | |
| "shoe": 772, | |
| "short": 773, | |
| "shout": 774, | |
| "show": 775, | |
| "sick": 776, | |
| "side": 777, | |
| "sight": 778, | |
| "sign": 779, | |
| "signal": 780, | |
| "silence": 781, | |
| "silent": 782, | |
| "silk": 783, | |
| "similar": 784, | |
| "simple": 785, | |
| "simulate": 786, | |
| "simulation": 787, | |
| "since": 788, | |
| "sing": 789, | |
| "single": 790, | |
| "sink": 791, | |
| "sit": 792, | |
| "situation": 793, | |
| "size": 794, | |
| "skin": 795, | |
| "sky": 796, | |
| "sleep": 797, | |
| "slow": 798, | |
| "small": 799, | |
| "smart": 800, | |
| "smile": 801, | |
| "smoke": 802, | |
| "snow": 803, | |
| "so": 804, | |
| "sock": 805, | |
| "soil": 806, | |
| "solar": 807, | |
| "solution": 808, | |
| "solve": 809, | |
| "something": 810, | |
| "song": 811, | |
| "soon": 812, | |
| "sound": 813, | |
| "space": 814, | |
| "special": 815, | |
| "species": 816, | |
| "speed": 817, | |
| "spike": 818, | |
| "spin": 819, | |
| "spoon": 820, | |
| "sport": 821, | |
| "spread": 822, | |
| "stable": 823, | |
| "stand": 824, | |
| "star": 825, | |
| "start": 826, | |
| "stay": 827, | |
| "steer": 828, | |
| "stellavore": 829, | |
| "sterling": 830, | |
| "stick": 831, | |
| "still": 832, | |
| "stony": 833, | |
| "stop": 834, | |
| "storage": 835, | |
| "stores": 836, | |
| "storm": 837, | |
| "story": 838, | |
| "strange": 839, | |
| "strict": 840, | |
| "strong": 841, | |
| "structure": 842, | |
| "student": 843, | |
| "study": 844, | |
| "stupid": 845, | |
| "subject": 846, | |
| "success": 847, | |
| "sudden": 848, | |
| "suddenly": 849, | |
| "sum": 850, | |
| "sun": 851, | |
| "sunrise": 852, | |
| "support": 853, | |
| "sure": 854, | |
| "surface": 855, | |
| "surprise": 856, | |
| "survival": 857, | |
| "survive": 858, | |
| "swim": 859, | |
| "switch": 860, | |
| "symbol": 861, | |
| "symbols": 862, | |
| "system": 863, | |
| "table": 864, | |
| "take": 865, | |
| "talk": 866, | |
| "tank": 867, | |
| "tap": 868, | |
| "task": 869, | |
| "taste": 870, | |
| "tea": 871, | |
| "teach": 872, | |
| "teacher": 873, | |
| "team": 874, | |
| "teamwork": 875, | |
| "tear": 876, | |
| "teeth": 877, | |
| "telephone": 878, | |
| "telescope": 879, | |
| "tell": 880, | |
| "temperature": 881, | |
| "territory": 882, | |
| "test": 883, | |
| "text": 884, | |
| "than": 885, | |
| "thank": 886, | |
| "that": 887, | |
| "the": 888, | |
| "theory": 889, | |
| "there": 890, | |
| "they": 891, | |
| "thing": 892, | |
| "think": 893, | |
| "this": 894, | |
| "thorn": 895, | |
| "through": 896, | |
| "thrust": 897, | |
| "thumb": 898, | |
| "thumbs": 899, | |
| "thunder": 900, | |
| "tied": 901, | |
| "tiger": 902, | |
| "tight": 903, | |
| "time": 904, | |
| "tiny": 905, | |
| "to": 906, | |
| "together": 907, | |
| "token": 908, | |
| "too": 909, | |
| "tool": 910, | |
| "topic": 911, | |
| "torch": 912, | |
| "touch": 913, | |
| "tough": 914, | |
| "towel": 915, | |
| "toxic": 916, | |
| "toxin": 917, | |
| "toy": 918, | |
| "trade": 919, | |
| "translate": 920, | |
| "translation": 921, | |
| "translator": 922, | |
| "transparent": 923, | |
| "travel": 924, | |
| "tree": 925, | |
| "triangle": 926, | |
| "trip": 927, | |
| "true": 928, | |
| "trumpet": 929, | |
| "trust": 930, | |
| "truth": 931, | |
| "try": 932, | |
| "tunnel": 933, | |
| "turn": 934, | |
| "under": 935, | |
| "understand": 936, | |
| "universe": 937, | |
| "unload": 938, | |
| "until": 939, | |
| "up": 940, | |
| "upgrade": 941, | |
| "urine": 942, | |
| "use": 943, | |
| "vacuum": 944, | |
| "valve": 945, | |
| "vega": 946, | |
| "vegetable": 947, | |
| "vehicle": 948, | |
| "vent": 949, | |
| "vibration": 950, | |
| "video": 951, | |
| "view": 952, | |
| "visible": 953, | |
| "vital": 954, | |
| "vitamin": 955, | |
| "volume": 956, | |
| "vote": 957, | |
| "wait": 958, | |
| "wake": 959, | |
| "walk": 960, | |
| "wall": 961, | |
| "want": 962, | |
| "warm": 963, | |
| "watch": 964, | |
| "water": 965, | |
| "wave": 966, | |
| "way": 967, | |
| "we": 968, | |
| "wear": 969, | |
| "weather": 970, | |
| "weigh": 971, | |
| "wet": 972, | |
| "what": 973, | |
| "when": 974, | |
| "where": 975, | |
| "while": 976, | |
| "white": 977, | |
| "who": 978, | |
| "why": 979, | |
| "will": 980, | |
| "win": 981, | |
| "wind": 982, | |
| "window": 983, | |
| "wire": 984, | |
| "with": 985, | |
| "without": 986, | |
| "wonder": 987, | |
| "wood": 988, | |
| "word": 989, | |
| "work": 990, | |
| "workshop": 991, | |
| "world": 992, | |
| "worth": 993, | |
| "write": 994, | |
| "wrong": 995, | |
| "year": 996, | |
| "yes": 997, | |
| "yesterday": 998, | |
| "young": 999, | |
| "zero": 1000 | |
| }, | |
| "unk_token": "[UNK]" | |
| } | |
| } |