image-match/python/py/Lib/site-packages/transformers/models/pixio/configuration_pixio.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/pixio/modular_pixio.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_pixio.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2025 Meta AI and The HuggingFace Inc. 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 ...backbone_utils import BackboneConfigMixin
from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring


@auto_docstring(checkpoint="facebook/pixio-huge")
@strict
class PixioConfig(BackboneConfigMixin, PreTrainedConfig):
    r"""
    apply_layernorm (`bool`, *optional*, defaults to `True`):
        Whether to apply layer normalization to the feature maps in case the model is used as backbone.
    reshape_hidden_states (`bool`, *optional*, defaults to `True`):
        Whether to reshape the feature maps to 4D tensors of shape `(batch_size, hidden_size, height, width)` in
        case the model is used as backbone. If `False`, the feature maps will be 3D tensors of shape `(batch_size,
        seq_len, hidden_size)`.
    n_cls_tokens (`int`, *optional*, defaults to 8):
        Number of class tokens in the Transformer encoder.

    Example:

    ```python
    >>> from transformers import PixioConfig, PixioModel

    >>> # Initializing a Pixio pixio-huge style configuration
    >>> configuration = PixioConfig()

    >>> # Initializing a model (with random weights) from the pixio-huge style configuration
    >>> model = PixioModel(configuration)

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

    model_type = "pixio"

    hidden_size: int = 1280
    num_hidden_layers: int = 32
    num_attention_heads: int = 16
    mlp_ratio: int = 4
    hidden_act: str = "gelu"
    hidden_dropout_prob: float | int = 0.0
    attention_probs_dropout_prob: float | int = 0.0
    initializer_range: float = 0.02
    layer_norm_eps: float = 1e-6
    image_size: int | list[int] | tuple[int, int] = 256
    patch_size: int | list[int] | tuple[int, int] = 16
    num_channels: int = 3
    qkv_bias: bool = True
    drop_path_rate: float | int = 0.0
    _out_features: list[str] | None = None
    _out_indices: list[int] | None = None
    apply_layernorm: bool = True
    reshape_hidden_states: bool = True
    n_cls_tokens: int = 8

    def __post_init__(self, **kwargs):
        self.stage_names = ["stem"] + [f"stage{idx}" for idx in range(1, self.num_hidden_layers + 1)]
        self.set_output_features_output_indices(
            out_indices=kwargs.pop("out_indices", None), out_features=kwargs.pop("out_features", None)
        )
        super().__post_init__(**kwargs)


__all__ = ["PixioConfig"]