"""Wind Edge configuration."""

from transformers.configuration_utils import PretrainedConfig


class WindEdgeConfig(PretrainedConfig):
    model_type = "wind_edge"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size: int = 151936,
        hidden_size: int = 1024,
        intermediate_size: int = 3072,
        num_hidden_layers: int = 28,
        num_attention_heads: int = 16,
        num_key_value_heads: int = 8,
        head_dim: int = 128,
        hidden_act: str = "silu",
        max_position_embeddings: int = 32768,
        initializer_range: float = 0.02,
        rms_norm_eps: float = 1e-6,
        use_cache: bool = True,
        tie_word_embeddings: bool = True,
        rope_theta: float = 1_000_000.0,
        attention_dropout: float = 0.0,
        attention_bias: bool = False,
        pad_token_id: int | None = None,
        bos_token_id: int = 151643,
        eos_token_id: int = 151643,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        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_key_value_heads = num_key_value_heads
        self.head_dim = head_dim
        self.hidden_act = hidden_act
        self.max_position_embeddings = max_position_embeddings
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.attention_dropout = attention_dropout
        self.attention_bias = attention_bias
        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )