#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/slanet/modular_slanet.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_slanet.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 The PaddlePaddle Team 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 consolidate_backbone_kwargs_to_config
from ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring
from ..auto import AutoConfig


@auto_docstring(checkpoint="PaddlePaddle/SLANet_plus_safetensors")
@strict
class SLANetConfig(PreTrainedConfig):
    r"""
    post_conv_out_channels (`int`, *optional*, defaults to 96):
        Number of output channels for the post-encoder convolution layer.
    out_channels (`int`, *optional*, defaults to 50):
        Vocabulary size for the table structure token prediction head, i.e., the number of distinct structure
        tokens the model can predict.
    hidden_size (`int`, *optional*, defaults to 256):
        Dimensionality of the hidden states in the attention GRU cell and the structure/location prediction heads.
    max_text_length (`int`, *optional*, defaults to 500):
        Maximum number of autoregressive decoding steps (tokens) for the structure and location decoder.
    csp_kernel_size (`int`, *optional*, defaults to 5):
        The kernel size of the Cross Stage Partial (CSP) layer.
    csp_num_blocks (`int`, *optional*, defaults to 1):
        Number of blocks within the Cross Stage Partial (CSP) layer.
    """

    model_type = "slanet"

    sub_configs = {"backbone_config": AutoConfig}
    post_conv_out_channels: int = 96
    out_channels: int = 50
    hidden_size: int = 256
    max_text_length: int = 500
    backbone_config: dict | PreTrainedConfig | None = None

    hidden_act: str = "hardswish"
    csp_kernel_size: int = 5
    csp_num_blocks: int = 1

    def __post_init__(self, **kwargs):
        self.backbone_config, kwargs = consolidate_backbone_kwargs_to_config(
            backbone_config=self.backbone_config,
            default_config_type="pp_lcnet",
            default_config_kwargs={
                "scale": 1,
                "out_features": ["stage2", "stage3", "stage4", "stage5"],
                "out_indices": [2, 3, 4, 5],
                "divisor": 16,
            },
            **kwargs,
        )
        super().__post_init__(**kwargs)


__all__ = ["SLANetConfig"]