from typing import Any

from transformers.configuration_utils import PretrainedConfig
from transformers import Qwen2Config

__all__ = ["AIMv2Config", "MonoConfig"]


class AIMv2Config(PretrainedConfig):

    model_type: str = "aimv2"

    def __init__(
        self,
        hidden_size: int = 1024,
        intermediate_size: int = 2816,
        num_hidden_layers: int = 24,
        num_attention_heads: int = 8,
        num_channels: int = 3,
        image_size: int = 224,
        patch_size: int = 14,
        rms_norm_eps: float = 1e-5,
        attention_dropout: float = 0.0,
        projection_dropout: float = 0.0,
        qkv_bias: bool = False,
        use_bias: bool = False,
        text_config=None,
        **kwargs: Any,
    ):
        super().__init__(**kwargs)
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.num_channels = num_channels
        self.patch_size = patch_size
        self.image_size = image_size
        self.attention_dropout = attention_dropout
        self.rms_norm_eps = rms_norm_eps

        self.projection_dropout = projection_dropout
        self.qkv_bias = qkv_bias
        self.use_bias = use_bias


class MonoConfig(Qwen2Config):

    model_type = "mono"
    is_composition = False

    def __init__(
        self,
        vision_config=None,
        ignore_index=-100,
        **kwargs,
    ):
        self.ignore_index = ignore_index
        if vision_config is not None:
            vision_config = AIMv2Config(**vision_config)
        self.vision_config = vision_config

        super().__init__(**kwargs)