#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
#           This file was automatically generated from src/transformers/models/got_ocr2/modular_got_ocr2.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_got_ocr2.py file directly. One of our CI enforces this.
#                🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
# Copyright 2024 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, SubConfigSpec
from ...utils import auto_docstring
from ..auto import AutoConfig


@auto_docstring(checkpoint="facebook/sam-vit-huge")
@strict
class GotOcr2VisionConfig(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"
    model_type = "got_ocr2_vision"

    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 | list[int] | tuple[int, int] = 1024
    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="facebook/sam-vit-huge")
@strict
class GotOcr2Config(PreTrainedConfig):
    r"""
    Example:

    ```python
    >>> from transformers import GotOcr2ForConditionalGeneration, GotOcr2Config

    >>> # Initializing a GotOcr2 style configuration
    >>> configuration = GotOcr2Config()

    >>> # Initializing a model from the Qwen2-VL-7B style configuration
    >>> model = GotOcr2ForConditionalGeneration(configuration)

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

    model_type = "got_ocr2"
    attribute_map = {"image_token_id": "image_token_index"}
    sub_configs_defaults = {
        "text_config": SubConfigSpec(
            config_class=AutoConfig,
            model_type="qwen2",
            init_kwargs={
                "vocab_size": 151860,
                "hidden_size": 1024,
                "intermediate_size": 2816,
                "num_hidden_layers": 24,
                "num_attention_heads": 16,
                "num_key_value_heads": 16,
                "hidden_act": "silu",
                "max_position_embeddings": 32768,
                "initializer_range": 0.02,
                "rms_norm_eps": 1e-6,
                "use_cache": True,
                "tie_word_embeddings": True,
                "rope_theta": 1000000.0,
                "rope_parameters": None,
                "use_sliding_window": False,
                "sliding_window": 4096,
                "max_window_layers": 21,
                "attention_dropout": 0.0,
            },
        ),
        "vision_config": SubConfigSpec(config_class=GotOcr2VisionConfig),
    }

    vision_config: dict | PreTrainedConfig | None = None
    text_config: dict | PreTrainedConfig | None = None
    image_token_index: int = 151859
    image_seq_length: int = 576
    tie_word_embeddings: bool = True


__all__ = ["GotOcr2VisionConfig", "GotOcr2Config"]