image-match/python/py/Lib/site-packages/transformers/models/aimv2/configuration_aimv2.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/aimv2/modular_aimv2.py.
#               Do NOT edit this file manually as any edits will be overwritten by the generation of
#             the file from the modular. If any change should be done, please apply the change to the
#                          modular_aimv2.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 Apple Inc. and The HuggingFace Team. All rights reserved.
#
# 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 huggingface_hub.dataclasses import strict

from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring, logging


logger = logging.get_logger(__name__)


@auto_docstring(checkpoint="apple/aimv2-large-patch14-224-lit")
@strict
class Aimv2VisionConfig(PreTrainedConfig):
    r"""
    use_head (`str`, *optional*, defaults to `True`):
        Whether to use Attention Pooling Head or Not.
    is_native (`str`, *optional*, defaults to `False`):
        Whether to use ckpt trained for image native resolution or not.

    Example:

    ```python
    >>> from transformers import SiglipVisionConfig, SiglipVisionModel

    >>> # Initializing a Aimv2VisionConfig with apple/aimv2-large-patch14-224 style configuration
    >>> configuration = Aimv2VisionConfig()

    >>> # Initializing a Aimv2VisionModel (with random weights) from the apple/aimv2-large-patch14-224 style configuration
    >>> model = Aimv2VisionModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "aimv2_vision_model"
    base_config_key = "vision_config"

    hidden_size: int = 1024
    intermediate_size: int = 2816
    num_hidden_layers: int = 24
    num_attention_heads: int = 8
    num_channels: int = 3
    image_size: int | list[int] | tuple[int, int] = 224
    patch_size: int | list[int] | tuple[int, int] = 14
    hidden_act: str = "silu"
    attention_dropout: float | int = 0.0
    rms_norm_eps: float = 1e-5
    qkv_bias: bool = False
    mlp_bias: bool = False
    initializer_range: float = 0.02
    use_head: bool = True
    is_native: bool = False


@auto_docstring(checkpoint="apple/aimv2-large-patch14-224-lit")
@strict
class Aimv2TextConfig(PreTrainedConfig):
    r"""
    Example:

    ```python
    >>> from transformers import Aimv2TextConfig, Aimv2TextModel

    >>> # Initializing a Aimv2TextConfig with google/aimv2-base-patch16-224 style configuration
    >>> configuration = Aimv2TextConfig()

    >>> # Initializing a Aimv2TextModel (with random weights) from the google/aimv2-base-patch16-224 style configuration
    >>> model = Aimv2TextModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "aimv2_text_model"
    base_config_key = "text_config"
    vocab_size: int = 49408
    hidden_size: int = 768
    intermediate_size: int = 2048
    num_hidden_layers: int = 12
    num_attention_heads: int = 6
    max_position_embeddings: int = 77
    hidden_act: str = "silu"
    attention_dropout: float | int = 0.0
    eos_token_id: int | list[int] | None = 49407
    rms_norm_eps: float = 1e-5
    qkv_bias: bool = False
    mlp_bias: bool = False
    initializer_range: float = 0.02

    def __post_init__(self, **kwargs):
        super().__post_init__(**kwargs)


@auto_docstring(checkpoint="apple/aimv2-large-patch14-224-lit")
@strict
class Aimv2Config(PreTrainedConfig):
    r"""
    max_logit_scale (`float`, *optional*, defaults to `100.0`):
        The maximum logit scale to use

    Example:

    ```python
    >>> from transformers import Aimv2Config, Aimv2Model

    >>> # Initializing a Aimv2Config with apple/aimv2-large-patch14-224-lit style configuration
    >>> configuration = Aimv2Config()

    >>> # Initializing a Aimv2Model (with random weights) from the apple/aimv2-large-patch14-224-lit style configuration
    >>> model = Aimv2Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config

    >>> # We can also initialize a Aimv2Config from a Aimv2TextConfig and a Aimv2VisionConfig
    >>> from transformers import Aimv2TextConfig, Aimv2VisionConfig

    >>> # Initializing a AIMv2Text and AIMv2Vision configuration
    >>> config_text = Aimv2TextConfig()
    >>> config_vision = Aimv2VisionConfig()

    >>> config = Aimv2Config(text_config=config_text, vision_config=config_vision)
    ```"""

    model_type = "aimv2"
    sub_configs = {"text_config": Aimv2TextConfig, "vision_config": Aimv2VisionConfig}

    text_config: dict | PreTrainedConfig | None = None
    vision_config: dict | PreTrainedConfig | None = None
    initializer_factor: float = 1.0

    projection_dim: int = 512
    logit_scale_init_value: float = 2.6592
    max_logit_scale: float = 100.0

    def __post_init__(self, **kwargs):
        if self.text_config is None:
            self.text_config = Aimv2TextConfig()
            logger.info("`text_config` is `None`. Initializing the `Aimv2TextConfig` with default values.")
        elif isinstance(self.text_config, dict):
            self.text_config = Aimv2TextConfig(**self.text_config)

        if self.vision_config is None:
            self.vision_config = Aimv2VisionConfig()
            logger.info("`vision_config` is `None`. initializing the `Aimv2VisionConfig` with default values.")
        elif isinstance(self.vision_config, dict):
            self.vision_config = Aimv2VisionConfig(**self.vision_config)

        super().__post_init__(**kwargs)


__all__ = ["Aimv2Config", "Aimv2VisionConfig", "Aimv2TextConfig"]