image-match/python/py/Lib/site-packages/transformers/models/slanext/configuration_slanext.py

#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/slanext/modular_slanext.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_slanext.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 ...configuration_utils import PreTrainedConfig
from ...utils import auto_docstring


@auto_docstring(checkpoint="PaddlePaddle/SLANeXt_wired_safetensors")
@strict
class SLANeXtVisionConfig(PreTrainedConfig):
    r"""
    output_channels (`int`, *optional*, defaults to 256):
        Dimensionality of the output channels in the Patch Encoder.
    use_abs_pos (`bool`, *optional*, defaults to `True`):
        Whether to use absolute position embedding.
    use_rel_pos (`bool`, *optional*, defaults to `True`):
        Whether to use relative position embedding.
    window_size (`int`, *optional*, defaults to 14):
        Window size for relative position.
    global_attn_indexes (`list[int]`, *optional*, defaults to `[2, 5, 8, 11]`):
        The indexes of the global attention layers.
    mlp_dim (`int`, *optional*, defaults to 3072):
        The dimensionality of the MLP layer in the Transformer encoder.
    """

    base_config_key = "vision_config"
    hidden_size: int = 768
    output_channels: int = 256
    num_hidden_layers: int = 12
    num_attention_heads: int = 12
    num_channels: int = 3
    image_size: int = 512
    patch_size: int | list[int] | tuple[int, int] = 16
    hidden_act: str = "gelu"
    layer_norm_eps: float = 1e-06
    attention_dropout: float | int = 0.0
    initializer_range: float = 1e-10
    qkv_bias: bool = True
    use_abs_pos: bool = True
    use_rel_pos: bool = True
    window_size: int = 14
    global_attn_indexes: list[int] | tuple[int, ...] = (2, 5, 8, 11)
    mlp_dim: int = 3072


@auto_docstring(checkpoint="PaddlePaddle/SLANeXt_wired_safetensors")
@strict
class SLANeXtConfig(PreTrainedConfig):
    r"""
    vision_config (`dict` or [`SLANeXtVisionConfig`], *optional*):
        Configuration for the vision encoder. If `None`, a default [`SLANeXtVisionConfig`] is used.
    post_conv_in_channels (`int`, *optional*, defaults to 256):
        Number of input channels for the post-encoder convolution layer.
    post_conv_out_channels (`int`, *optional*, defaults to 512):
        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 512):
        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.
    """

    model_type = "slanext"
    sub_configs = {"vision_config": SLANeXtVisionConfig}

    vision_config: dict | SLANeXtVisionConfig | None = None
    post_conv_in_channels: int = 256
    post_conv_out_channels: int = 512
    out_channels: int = 50
    hidden_size: int = 512
    max_text_length: int = 500

    def __post_init__(self, **kwargs):
        if self.vision_config is None:
            self.vision_config = SLANeXtVisionConfig()
        elif isinstance(self.vision_config, dict):
            self.vision_config = SLANeXtVisionConfig(**self.vision_config)
        super().__post_init__(**kwargs)


__all__ = ["SLANeXtConfig"]