from __future__ import annotations

from collections.abc import Iterable

from transformers.configuration_utils import PretrainedConfig


class UltrabertConfig(PretrainedConfig):
    model_type = "ultrabert"

    def __init__(
        self,
        vocab_size=32000,
        hidden_size=4096,
        intermediate_size=11008,
        prediction_head_size=None,
        num_hidden_layers=32,
        num_attention_heads=32,
        num_key_value_heads=None,
        attention_windows=None,
        hidden_act="silu",
        initializer_range=0.02,
        rms_norm_eps=1e-6,
        pad_token_id=0,
        bos_token_id=0,
        eos_token_id=0,
        tie_word_embeddings=False,
        rope_theta=10000.0,
        attention_bias=False,
        attention_dropout=0.0,
        mlp_bias=False,
        head_dim=None,
        classifier_dropout=0.0,
        **kwargs,
    ):
        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_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.prediction_head_size = prediction_head_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.num_key_value_heads = num_key_value_heads or num_attention_heads
        self.attention_windows = (
            attention_windows
            if isinstance(attention_windows, Iterable)
            else [attention_windows] * num_hidden_layers
        )
        self.hidden_act = hidden_act
        self.initializer_range = initializer_range
        self.rms_norm_eps = rms_norm_eps
        self.rope_theta = (
            rope_theta
            if isinstance(rope_theta, Iterable)
            else [rope_theta] * num_hidden_layers
        )
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout
        self.mlp_bias = mlp_bias
        self.head_dim = head_dim or self.hidden_size // self.num_attention_heads
        self.classifier_dropout = classifier_dropout