"""AQ model configuration.

AQ (Academic Quotient) — Zyora Labs' proprietary, from-scratch decoder
architecture: RMSNorm, rotary position embeddings, grouped-query attention,
SwiGLU feed-forward, tied embeddings.
"""

from transformers import PretrainedConfig


class AQConfig(PretrainedConfig):
    model_type = "aq"

    def __init__(
        self,
        vocab_size: int = 32000,
        hidden_size: int = 1536,
        intermediate_size: int = 4096,
        num_hidden_layers: int = 48,
        num_attention_heads: int = 24,
        num_key_value_heads: int = 8,
        head_dim: int = 64,
        max_position_embeddings: int = 2048,
        rope_theta: float = 10000.0,
        rms_norm_eps: float = 1e-5,
        tie_word_embeddings: bool = True,
        bos_token_id: int = 0,
        eos_token_id: int = 0,
        pad_token_id: int = 0,
        **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.max_position_embeddings = max_position_embeddings
        self.rope_theta = rope_theta
        self.rms_norm_eps = rms_norm_eps
        super().__init__(
            tie_word_embeddings=tie_word_embeddings,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            pad_token_id=pad_token_id,
            **kwargs,
        )