peft/tuners/ia3/config.py

# Copyright 2023-present the HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from dataclasses import dataclass, field
from typing import List, Optional, Union

from peft.config import PeftConfig
from peft.utils import PeftType


@dataclass
class IA3Config(PeftConfig):
    """
    This is the configuration class to store the configuration of a [`IA3Model`].

    Args:
        target_modules (`Optional[Union[List[str], str]]`):
            The names of the modules to apply the adapter to. If this is specified, only the modules with the specified
            names will be replaced. When passing a string, a regex match will be performed. When passing a list of
            strings, either an exact match will be performed or it is checked if the name of the module ends with any
            of the passed strings. If this is specified as 'all-linear', then all linear/Conv1D modules are chosen,
            excluding the output layer. If this is not specified, modules will be chosen according to the model
            architecture. If the architecture is not known, an error will be raised -- in this case, you should specify
            the target modules manually.
        feedforward_modules (`Optional[Union[List[str], str]]`):
            The names of the modules to be treated as feedforward modules, as in the original paper. These modules will
            have (IA)³ vectors multiplied to the input, instead of the output. `feedforward_modules` must be a name or
            a subset of names present in `target_modules`.
        fan_in_fan_out (`bool`):
            Set this to True if the layer to replace stores weight like (fan_in, fan_out). For example, gpt-2 uses
            `Conv1D` which stores weights like (fan_in, fan_out) and hence this should be set to `True`.
        modules_to_save (`Optional[List[str]]`):
            List of modules apart from (IA)³ layers to be set as trainable and saved in the final checkpoint.
        init_ia3_weights (`bool`):
            Whether to initialize the vectors in the (IA)³ layers, defaults to `True`. Setting this to `False` is
            discouraged.
    """

    target_modules: Optional[Union[List[str], str]] = field(
        default=None,
        metadata={
            "help": (
                "List of module names or regex expression of the module names to replace with (IA)³."
                "For example, ['q', 'v'] or '.*decoder.*(SelfAttention|EncDecAttention).*(q|v)$'."
                "This can also be a wildcard 'all-linear' which matches all linear/Conv1D layers except the output layer."
                "If not specified, modules will be chosen according to the model architecture, If the architecture is "
                "not known, an error will be raised -- in this case, you should specify the target modules manually."
            ),
        },
    )
    feedforward_modules: Optional[Union[List[str], str]] = field(
        default=None,
        metadata={
            "help": "List of module names or a regex expression of module names which are feedforward"
            "For example, ['output.dense']"
        },
    )
    fan_in_fan_out: bool = field(
        default=False,
        metadata={"help": "Set this to True if the layer to replace stores weight like (fan_in, fan_out)"},
    )
    modules_to_save: Optional[List[str]] = field(
        default=None,
        metadata={
            "help": "List of modules apart from (IA)^3 layers to be set as trainable and saved in the final checkpoint. "
            "For example, in Sequence Classification or Token Classification tasks, "
            "the final layer `classifier/score` are randomly initialized and as such need to be trainable and saved."
        },
    )
    init_ia3_weights: bool = field(
        default=True,
        metadata={"help": "Whether to initialize the vectors in the (IA)^3 layers."},
    )

    def __post_init__(self):
        self.peft_type = PeftType.IA3
        self.target_modules = (
            set(self.target_modules) if isinstance(self.target_modules, list) else self.target_modules
        )
        self.feedforward_modules = (
            set(self.feedforward_modules) if isinstance(self.feedforward_modules, list) else self.feedforward_modules
        )

        # check if feedforward_modules is a subset of target_modules. run the check only if both are sets
        if isinstance(self.feedforward_modules, set) and isinstance(self.target_modules, set):
            if not self.feedforward_modules.issubset(self.target_modules):
                raise ValueError("`feedforward_modules` should be a subset of `target_modules`")