Method add_adapter

src/peft/peft_model.py:1020–1096

Add an adapter to the model based on the passed configuration. This adapter is not trained. To load a trained adapter, check out [`PeftModel.load_adapter`]. The name for the new adapter should be unique. The new adapter is not automatically set as the active adapt

(
        self,
        adapter_name: str,
        peft_config: PeftConfig,
        low_cpu_mem_usage: bool = False,
        autocast_adapter_dtype: bool = True,
    )

        return self.base_model if self.active_peft_config.is_prompt_learning else self.base_model.model

    def add_adapter(
        self,
        adapter_name: str,
        peft_config: PeftConfig,
        low_cpu_mem_usage: bool = False,
        autocast_adapter_dtype: bool = True,
    ) -> None:
        """
        Add an adapter to the model based on the passed configuration.

        This adapter is not trained. To load a trained adapter, check out [`PeftModel.load_adapter`].

        The name for the new adapter should be unique.

        The new adapter is not automatically set as the active adapter. Use [`PeftModel.set_adapter`] to set the active
        adapter.

        Args:
            adapter_name (`str`):
                The name of the adapter to be added.
            peft_config ([`PeftConfig`]):
                The configuration of the adapter to be added.
            low_cpu_mem_usage (`bool`, `optional`, defaults to `False`):
                Create empty adapter weights on meta device. Useful to speed up the process when loading saved
                adapters. Don't use this option when creating a new PEFT adapter for training.
            autocast_adapter_dtype (`bool`, *optional*, defaults to `True`):
                Whether to autocast the adapter dtype. Defaults to `True`. Right now, this will only cast adapter
                weights using float16 and bfloat16 to float32, as this is typically required for stable training, and
                only affect select PEFT tuners. If set to `False`, the dtypes will stay the same as those of the
                corresponding layer.
        """
        prefix = PEFT_TYPE_TO_PREFIX_MAPPING.get(peft_config.peft_type)
        if prefix and adapter_name in prefix:
            warnings.warn(
                f"Adapter name '{adapter_name}' should not be contained in the prefix '{prefix}'. "
                "This may lead to reinitialization of the adapter weights during loading."
            )

        if peft_config.peft_type != self.peft_type:
            raise ValueError(
                f"Cannot combine adapters with different peft types. "
                f"Found {self.peft_type} and {peft_config.peft_type}."
            )

        try:
            if peft_config.is_prompt_learning:
                self.peft_config[adapter_name] = peft_config
                peft_config = _prepare_prompt_learning_config(peft_config, self.config)
                self._setup_prompt_encoder(adapter_name)
                set_additional_trainable_modules(
                    model=self.base_model,
                    peft_config=peft_config,
                    model_config=BaseTuner.get_model_config(self),
                    adapter_name=adapter_name,
                )
            elif peft_config.is_adaption_prompt:
                self.base_model.add_adapter(adapter_name, peft_config)
                set_additional_trainable_modules(