from transformers import LlamaConfig

class CognitivessConfig(LlamaConfig):
    model_type = "cognitivess"

    def __init__(
        self,
        vocab_size=128256,
        hidden_size=4096,
        intermediate_size=14336,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=8,
        hidden_act="silu",
        max_position_embeddings=8192,
        initializer_range=0.02,
        rms_norm_eps=1e-5,
        use_cache=True,
        pad_token_id=0,
        bos_token_id=128000,
        eos_token_id=128001,
        tie_word_embeddings=False,
        attention_dropout=0.0,
        pretraining_tp=1,
        rope_theta=500000.0,
        **kwargs
    ):
        super().__init__(
            vocab_size=vocab_size,
            hidden_size=hidden_size,
            intermediate_size=intermediate_size,
            num_hidden_layers=num_hidden_layers,
            num_attention_heads=num_attention_heads,
            num_key_value_heads=num_key_value_heads,
            hidden_act=hidden_act,
            max_position_embeddings=max_position_embeddings,
            initializer_range=initializer_range,
            rms_norm_eps=rms_norm_eps,
            use_cache=use_cache,
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            tie_word_embeddings=tie_word_embeddings,
            pretraining_tp=pretraining_tp,
            rope_theta=rope_theta,
            **kwargs
        )
        self.attention_dropout = attention_dropout