from transformers import PretrainedConfig

class C2LLMConfig(PretrainedConfig):
    model_type = "c2llm"
    keys_to_ignore_at_inference = ["past_key_values"]

    base_model_tp_plan = {
        "layers.*.self_attn.q_proj": "colwise",
        "layers.*.self_attn.k_proj": "colwise",
        "layers.*.self_attn.v_proj": "colwise",
        "layers.*.self_attn.o_proj": "rowwise",
        "layers.*.mlp.gate_proj": "colwise",
        "layers.*.mlp.up_proj": "colwise",
        "layers.*.mlp.down_proj": "rowwise",
    }
    base_model_pp_plan = {
        "embed_tokens": (["input_ids"], ["inputs_embeds"]),
        "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
        "norm": (["hidden_states"], ["hidden_states"]),
    }


    def __init__(
        self,
        attention_dropout=0.0,
        bos_token_id=151643,
        eos_token_id=151645,
        hidden_act="silu",
        hidden_size=3584,
        initializer_range=0.02,
        intermediate_size=18944,
        max_position_embeddings=32768,
        max_window_layers=28,
        model_type="c2llm",
        num_attention_heads=28,
        num_hidden_layers=28,
        num_key_value_heads=4,
        rms_norm_eps=1e-6,
        rope_theta=1000000.0,
        sliding_window=131072,
        tie_word_embeddings=False,
        torch_dtype="bfloat16",
        transformers_version="4.43.1",
        use_cache=True,
        use_sliding_window=False,
        vocab_size=152064,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        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.use_sliding_window = use_sliding_window
        self.sliding_window = sliding_window if use_sliding_window else None
        self.max_window_layers = max_window_layers

        # for backward compatibility
        if num_key_value_heads is None:
            num_key_value_heads = num_attention_heads

        self.num_key_value_heads = num_key_value_heads
        self.hidden_act = hidden_act
        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

        super().__init__(
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )
    def to_dict(self):
        output = super().to_dict()
        
        keys_to_remove = [
            "base_model"
        ]
        
        for key in keys_to_remove:
            output.pop(key, None)
            
        return output
        
__all__ = ["C2LLMConfig"]