from transformers import PretrainedConfig
from transformers.utils import logging

logger = logging.get_logger(__name__)

HIERBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "igorktech/custom4": "https://huggingface.co./igorktech/custom4/resolve/main/config.json",
    "igorktech/custom4": "https://huggingface.co./igorktech/custom4/resolve/main/config.json",
}


class HierBertConfig(PretrainedConfig):
    r"""
        This is the configuration class to store the configuration of a [`HierBertModel`]. It is used to
        instantiate a HierBERT model according to the specified arguments, defining the model architecture. Instantiating a
        configuration with the defaults will yield a similar configuration to that of the HierBERT
        [HierBert](https://github.com/igorktech/hier-bert-pytorch) architecture.

        Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
        documentation from [`PretrainedConfig`] for more information.


        Args:
            vocab_size (`int`, *optional*, defaults to 30522):
                Vocabulary size of the BERT model. Defines the number of different tokens that can be represented by the
                `inputs_ids` passed when calling [`BertModel`] or [`TFBertModel`].
            hidden_size (`int`, *optional*, defaults to 768):
                Dimensionality of the encoder layers and the pooler layer.
            num_hidden_layers (`int`, *optional*, defaults to 12):
                Number of hidden layers in the Transformer encoder.
            num_attention_heads (`int`, *optional*, defaults to 12):
                Number of attention heads for each attention layer in the Transformer encoder.
            intermediate_size (`int`, *optional*, defaults to 3072):
                Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
            hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`):
                The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
                `"relu"`, `"silu"` and `"gelu_new"` are supported.
            hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
                The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
            attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1):
                The dropout ratio for the attention probabilities.
            max_position_embeddings (`int`, *optional*, defaults to 512):
                The maximum sequence length that this model might ever be used with. Typically set this to something large
                just in case (e.g., 512 or 1024 or 2048).
            type_vocab_size (`int`, *optional*, defaults to 2):
                The vocabulary size of the `token_type_ids` passed when calling [`BertModel`] or [`TFBertModel`].
            initializer_range (`float`, *optional*, defaults to 0.02):
                The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
            layer_norm_eps (`float`, *optional*, defaults to 1e-12):
                The epsilon used by the layer normalization layers.
            position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
                Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
                positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
                [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
                For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
                with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
            is_decoder (`bool`, *optional*, defaults to `False`):
                Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
            use_cache (`bool`, *optional*, defaults to `True`):
                Whether or not the model should return the last key/values attentions (not used by all models). Only
                relevant if `config.is_decoder=True`.
            classifier_dropout (`float`, *optional*):
                The dropout ratio for the classification head.
        """

    model_type = "hierarchical-bert"

    def __init__(
            self,
            vocab_size=32000,
            hidden_size=512,
            num_hidden_layers=6,
            num_attention_heads=8,
            intermediate_size=2048,
            hidden_act="gelu",
            hidden_dropout_prob=0.1,
            attention_probs_dropout_prob=0.1,
            max_position_embeddings=512,
            type_vocab_size=2,
            initializer_range=0.02,
            layer_norm_eps=1e-6,
            norm_first=True,
            pad_token_id=0,
            sep_token_id=3,
            position_embedding_type="absolute",
            use_cache=True,
            classifier_dropout=None,
            auto_map={
                "AutoConfig": "configuration_hier.HierBertConfig",
                "AutoModel": "modelling_hier.HierBertModel",
                "AutoModelForMaskedLM": "modelling_hier.HierBertForMaskedLM",
                "AutoModelForSequenceClassification": "modelling_hier.HierBertForSequenceClassification",
            },
            **kwargs,
    ):
        super().__init__(
            pad_token_id=pad_token_id,
            sep_token_id=sep_token_id,
            **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.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.norm_first = norm_first
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.classifier_dropout = classifier_dropout
        self.auto_map = auto_map