from transformers import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)


class CodeFuseCGELargeConfig(PretrainedConfig):
    model_type = "qwen2"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=151936,
        hidden_size=4096,
        intermediate_size=22016,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=32,
        hidden_act="silu",
        max_position_embeddings=32768,
        initializer_range=0.02,
        rms_norm_eps=1e-6,
        use_cache=True,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        use_sliding_window=False,
        sliding_window=4096,
        max_window_layers=28,
        attention_dropout=0.0,
        embedding_method="pma",
        inf_seq_length=1024,
        padding_side="right",
        compress_dim=1024,
        keep_max_layer=32,
        pma_num_heads=32,
        pma_ln=True,
        pma_norm=False,
        pma_norm_mode="post_normal",
        **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

        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

        self.embedding_method = embedding_method
        self.inf_seq_length = inf_seq_length
        self.padding_side = padding_side
        self.compress_dim = compress_dim
        self.keep_max_layer = keep_max_layer
        self.pma_num_heads = pma_num_heads
        self.pma_ln = pma_ln
        self.pma_norm = pma_norm
        self.pma_norm_mode = pma_norm_mode

        super().__init__(
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )