from transformers import PretrainedConfig


class NovaConfig(PretrainedConfig):
    model_type = "nova"

    def __init__(
        self,
        vocab_size=32768,
        hidden_size=640,
        num_hidden_layers=26,
        num_attention_heads=10,
        num_key_value_heads=5,
        head_dim=64,
        intermediate_size=1920,
        max_position_embeddings=2048,
        rope_theta=100000.0,
        **kwargs,
    ):
        super().__init__(tie_word_embeddings=True, **kwargs)
        self.vocab_size = vocab_size
        self.hidden_size = hidden_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.intermediate_size = intermediate_size
        self.max_position_embeddings = max_position_embeddings
        self.rope_theta = rope_theta