#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/lighton_ocr/modular_lighton_ocr.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_lighton_ocr.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2026 The LightOn 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 typing import Any

from ...configuration_utils import PretrainedConfig
from ..auto import CONFIG_MAPPING, AutoConfig


class LightOnOcrConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`LightOnOcrForConditionalGeneration`]. It is used to instantiate a
    LightOnOcr model according to the specified arguments, defining the model architecture.

    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information. Instantiating a configuration with the defaults will yield
    a similar configuration to that of the LightOnOcr [lightonocr-hf/lightonocr-9b](https://huggingface.co/lightonocr-hf/lightonocr-9b) architecture.

    Args:
        spatial_merge_size (`int`, *optional*, defaults to 2):
            The size of spatial merging for image patches.
        image_token_id (`int`, *optional*, defaults to 151655):
            The id of the image token in the vocabulary.
        tie_word_embeddings (`bool`, *optional*, defaults to `True`):
            Whether the model's input and output word embeddings should be tied.
        vision_config (`dict` or `LightOnOcrVisionConfig`, *optional*):
            Custom vision configuration or dictionary with vision configuration values.
        text_config (`dict` or `LightOnOcrTextConfig`, *optional*):
            Custom text configuration or dictionary with text configuration values.

    Example:

    ```python
    >>> from transformers import LightOnOcrConfig, LightOnOcrForConditionalGeneration

    >>> # Initializing a LightOnOcr configuration
    >>> configuration = LightOnOcrConfig()

    >>> # Initializing a model from the configuration
    >>> model = LightOnOcrForConditionalGeneration(configuration)

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

    model_type = "lighton_ocr"
    sub_configs = {"text_config": AutoConfig, "vision_config": AutoConfig}

    def __init__(
        self,
        spatial_merge_size: int = 2,
        image_token_id: int = 151655,
        tie_word_embeddings: bool = True,
        vision_config: dict[str, Any] | None = None,
        text_config: dict[str, Any] | None = None,
        **kwargs,
    ):
        self.spatial_merge_size = spatial_merge_size
        self.image_token_id = image_token_id
        self.tie_word_embeddings = tie_word_embeddings

        if vision_config is None:
            self.vision_config = CONFIG_MAPPING["pixtral"](
                attention_dropout=0,
                head_dim=64,
                hidden_act="silu",
                hidden_size=1024,
                image_size=1540,
                initializer_range=0.02,
                intermediate_size=4096,
                model_type="pixtral",
                num_attention_heads=16,
                num_channels=3,
                num_hidden_layers=24,
                patch_size=14,
                rope_theta=10000,
            )
        elif isinstance(vision_config, PretrainedConfig):
            self.vision_config = vision_config
        else:
            vision_config["model_type"] = vision_config.get("model_type", "pixtral")
            self.vision_config = CONFIG_MAPPING[vision_config["model_type"]](**vision_config)

        if text_config is None:
            self.text_config = CONFIG_MAPPING["qwen3"](
                attention_dropout=0,
                head_dim=128,
                hidden_act="silu",
                hidden_size=1024,
                initializer_range=0.02,
                intermediate_size=3072,
                max_position_embeddings=40960,
                num_attention_heads=16,
                num_hidden_layers=28,
                num_key_value_heads=8,
                rms_norm_eps=1e-6,
                rope_theta=1000000,
                sliding_window=None,
                use_cache=True,
                vocab_size=151936,
            )
        elif isinstance(text_config, PretrainedConfig):
            self.text_config = text_config
        else:
            text_config["model_type"] = text_config.get("model_type", "qwen3")
            self.text_config = CONFIG_MAPPING[text_config["model_type"]](**text_config)

        super().__init__(**kwargs)


__all__ = ["LightOnOcrConfig"]