Llama 3

    num_reserved_special_tokens = 256

    pat_str = r"(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}{1,3}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"  # noqa: E501

… lines 48–55 omitted …

        assert os.path.isfile(model_path), model_path

        mergeable_ranks = load_tiktoken_bpe(model_path)
        num_base_tokens = len(mergeable_ranks)
        special_tokens = [
            "<|begin_of_text|>",
            "<|end_of_text|>",
            "<|reserved_special_token_0|>",
            "<|reserved_special_token_1|>",
            "<|reserved_special_token_2|>",
            "<|reserved_special_token_3|>",
            "<|start_header_id|>",
            "<|end_header_id|>",
            "<|reserved_special_token_4|>",
            "<|eot_id|>",  # end of turn
        ] + [
            f"<|reserved_special_token_{i}|>"
            for i in range(5, self.num_reserved_special_tokens - 5)
        ]
        self.special_tokens = {
            token: num_base_tokens + i for i, token in enumerate(special_tokens)
        }
        self.model = tiktoken.Encoding(
            name=Path(model_path).name,
            pat_str=self.pat_str,
            mergeable_ranks=mergeable_ranks,
            special_tokens=self.special_tokens,
        )

… lines 84–146 omitted …

        t: List[int] = []
        for substr in substrs:
            t.extend(
                self.model.encode(
                    substr,
                    allowed_special=allowed_special,
                    disallowed_special=disallowed_special,
                )
            )
        if bos:
            t.insert(0, self.bos_id)
        if eos:
            t.append(self.eos_id)
        return t

        prompt_tokens = [self.tokenizer.encode(x, bos=True, eos=False) for x in prompts]