Method __init__

llama_cpp/llama_chat_format.py:205–236

A chat formatter that uses jinja2 templates to format the prompt.

(
        self,
        template: str,
        eos_token: str,
        bos_token: str,
        add_generation_prompt: bool = True,
        stop_token_ids: Optional[List[int]] = None,
    )

            return parser.parse_statements(("name:endgeneration",), drop_needle=True)

    def __init__(
        self,
        template: str,
        eos_token: str,
        bos_token: str,
        add_generation_prompt: bool = True,
        stop_token_ids: Optional[List[int]] = None,
    ):
        """A chat formatter that uses jinja2 templates to format the prompt."""
        self.template = template
        self.eos_token = eos_token
        self.bos_token = bos_token
        self.add_generation_prompt = add_generation_prompt
        self.stop_token_ids = (
            set(stop_token_ids) if stop_token_ids is not None else None
        )

        environment = ImmutableSandboxedEnvironment(
            loader=jinja2.BaseLoader(),
            trim_blocks=True,
            lstrip_blocks=True,
            # Keep this aligned with Transformers' chat-template Jinja extensions.
            # https://github.com/huggingface/transformers/blob/39603d0e5cdb6f00e8d473d7fcbb01032d709181/src/transformers/utils/chat_template_utils.py#L489-L490
            extensions=[
                Jinja2ChatFormatter.IgnoreGenerationTags,
                jinja2.ext.loopcontrols,
            ],
        )
        # Match Transformers' chat-template JSON rendering behavior.
        # https://github.com/huggingface/transformers/blob/39603d0e5cdb6f00e8d473d7fcbb01032d709181/src/transformers/utils/chat_template_utils.py#L481-L484
        environment.filters["tojson"] = self.tojson
        self._environment = environment.from_string(self.template)

    @staticmethod
    def strftime_now(f: str) -> str: