from transformers.configuration_utils import PretrainedConfig


class DynamicMindMoEConfig(PretrainedConfig):
    """DynamicMind-MoE: sparse mixture-of-experts variant of DynamicMind-Mini.

    The dense MLP (intermediate 768) is replaced by one always-on shared expert
    plus `num_routed_experts` fine-grained experts (intermediate 256), of which
    `num_experts_per_token` are selected. Shared + top-2 reproduces the dense
    layer's exact active parameter count, so inference cost per token is
    unchanged while total capacity grows ~3.4x.
    """

    model_type = "dynamicmind_moe"

    def __init__(
        self,
        vocab_size=8192,
        hidden_size=256,
        intermediate_size=768,        # kept for dense layers / upcycling source
        moe_intermediate_size=256,    # per-expert width (768 / 3)
        num_hidden_layers=9,
        num_attention_heads=8,
        num_key_value_heads=2,
        num_routed_experts=14,
        num_shared_experts=1,
        num_experts_per_token=2,
        first_k_dense_layers=0,       # keep the first K blocks dense if desired
        norm_topk_prob=True,
        router_aux_loss_coef=0.01,
        router_z_loss_coef=0.001,
        router_bias_update_rate=0.001,  # aux-loss-free balancing (DeepSeek-V3)
        use_aux_loss_free_balancing=True,
        max_position_embeddings=1024,
        rms_norm_eps=1e-5,
        rope_theta=10000.0,
        attention_dropout=0.0,
        tie_word_embeddings=True,
        bos_token_id=0,
        eos_token_id=0,
        pad_token_id=1,
        **kwargs,
    ):
        super().__init__(
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            pad_token_id=pad_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )

        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.moe_intermediate_size = moe_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.num_routed_experts = num_routed_experts
        self.num_shared_experts = num_shared_experts
        self.num_experts_per_token = num_experts_per_token
        self.first_k_dense_layers = first_k_dense_layers
        self.norm_topk_prob = norm_topk_prob

        self.router_aux_loss_coef = router_aux_loss_coef
        self.router_z_loss_coef = router_z_loss_coef
        self.router_bias_update_rate = router_bias_update_rate
        self.use_aux_loss_free_balancing = use_aux_loss_free_balancing

        self.max_position_embeddings = max_position_embeddings
        self.rms_norm_eps = rms_norm_eps
        self.rope_theta = rope_theta
        self.attention_dropout = attention_dropout