Method encode

model/tokenizer.py:30–37

(self, s: str, bos: bool, eos: bool)

        assert self.sp_model.vocab_size() == self.sp_model.get_piece_size()

    def encode(self, s: str, bos: bool, eos: bool) -> List[int]:
        assert type(s) is str
        t = self.sp_model.encode(s)
        if bos:
            t = [self.bos_id] + t
        if eos:
            t = t + [self.eos_id]
        return t

    def decode(self, t: List[int]) -> str:
        return self.sp_model.decode(t)