"""
Eruku Configuration

Configuration class for the Eruku Styled Handwritten Text Recognition model.
"""

from transformers import PretrainedConfig


class ErukuConfig(PretrainedConfig):
    """
    Configuration class for Eruku model.
    
    Args:
        t5_name_or_path (`str`, *optional*, defaults to `"google-t5/t5-large"`):
            The name or path of the T5 model to use as the backbone.
        vae_name_or_path (`str`, *optional*, defaults to `"blowing-up-groundhogs/emuru_vae"`):
            The name or path of the VAE model for image encoding/decoding.
        tokenizer_name_or_path (`str`, *optional*, defaults to `"google/byt5-small"`):
            The name or path of the tokenizer (character-level).
        slices_per_query (`int`, *optional*, defaults to 1):
            Number of VAE latent slices per query token.
        channels (`int`, *optional*, defaults to 1):
            Number of channels in the VAE latent space.
        vae_latent_dim (`int`, *optional*, defaults to 8):
            Dimension of the VAE latent space.
        cfg_scale (`float`, *optional*, defaults to 1.25):
            Default classifier-free guidance scale for generation.
    """
    
    model_type = "eruku"
    
    def __init__(
        self,
        t5_name_or_path: str = "google-t5/t5-large",
        vae_name_or_path: str = "blowing-up-groundhogs/emuru_vae",
        tokenizer_name_or_path: str = "google/byt5-small",
        slices_per_query: int = 1,
        channels: int = 1,
        vae_latent_dim: int = 8,
        cfg_scale: float = 1.25,
        **kwargs
    ):
        super().__init__(**kwargs)
        self.t5_name_or_path = t5_name_or_path
        self.vae_name_or_path = vae_name_or_path
        self.tokenizer_name_or_path = tokenizer_name_or_path
        self.slices_per_query = slices_per_query
        self.channels = channels
        self.vae_latent_dim = vae_latent_dim
        self.cfg_scale = cfg_scale