| {"d": 13, "Ġquick": 104, "Th": 39, "Ġbrown": 103, "Ġvocabulary": 106, "w": 31, "qu": 71, "ular": 75, "u": 29, "vocab": 76, "o": 23, "m": 21, "Ġtoken": 86, "The": 90, "Sa": 52, "s": 27, "M": 7, "Ġt": 36, "sim": 74, "a": 10, "Ġfor": 94, "<|im_end|>": 3, "Ġwor": 85, "h": 17, "xt": 78, "Ġa": 79, "t": 28, "Ġsim": 83, "Sample": 99, "Ġtest": 48, "p": 24, "y": 33, "c": 12, "Ġ": 35, "ab": 53, "sic": 73, "Ġis": 80, "<|endoftext|>": 1, "Ba": 49, "Ġsimple": 105, "Ġvocab": 84, "Ġworld": 107, "Ġfo": 47, "en": 59, "T": 9, "b": 11, "i": 18, "Ġtrain": 87, "wor": 77, "n": 22, "q": 25, "own": 101, "Minimal": 98, "Hell": 97, "ow": 68, "Ġtraining": 109, "H": 6, "x": 32, "fo": 40, "mple": 66, "ken": 62, "ing": 88, "Ġte": 38, "Hello": 110, "iz": 61, "im": 42, "Ġtext": 89, "Min": 51, "He": 50, "k": 19, "Ġqu": 82, "ple": 45, "A": 4, "f": 15, "<unk>": 0, "Basic": 96, "or": 67, "B": 5, "S": 8, "lar": 65, "imal": 93, "v": 30, "al": 54, "This": 91, "oken": 70, "br": 57, "l": 20, "cab": 58, "er": 60, "ain": 56, "ick": 92, "izer": 100, "<|im_start|>": 2, "ar": 55, "Ġbr": 81, "g": 16, "Ġtokenizer": 108, "st": 46, "ld": 63, "r": 26, "ll": 64, "e": 14, "ocab": 69, "le": 44, "is": 43, "ulary": 102, "rain": 72, "in": 37, "Ġfox": 95, "z": 34, "ic": 41} |