# coding=utf-8
# Copyright 2019-present, the HuggingFace Inc. team, The Google AI Language Team and Facebook, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" LddBERT model configuration"""
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

LDDBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    # "lddbert-base-uncased": "https://huggingface.co/lddbert-base-uncased/resolve/main/config.json",
}


class LddBertConfig(PretrainedConfig):
    r"""
    模型配置。

    Args:
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the LddBERT model. Defines the number of different tokens that can be represented by
            the `inputs_ids` passed when calling [`LddBertModel`] or [`TFLddBertModel`].
        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).
        sinusoidal_pos_embds (`boolean`, *optional*, defaults to `False`):
            Whether to use sinusoidal positional embeddings.
        n_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        n_gru_layers (`int`, *optional*, defaults to 1):
            GRU 层数.
        n_heads (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        dim (`int`, *optional*, defaults to 768):
            Dimensionality of the encoder layers and the pooler layer.
        hidden_dim (`int`, *optional*, defaults to 3072):
            The size of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        activation (`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.
        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.
        qa_dropout (`float`, *optional*, defaults to 0.1):
            The dropout probabilities used in the question answering model [`LddBertForQuestionAnswering`].
        seq_classif_dropout (`float`, *optional*, defaults to 0.2):
            The dropout probabilities used in the sequence classification and the multiple choice model
            [`LddBertForSequenceClassification`].

    Examples:

    ```python
    >>> from transformers import LddBertModel, LddBertConfig

    >>> # Initializing a LddBERT configuration
    >>> configuration = LddBertConfig()

    >>> # Initializing a model from the configuration
    >>> model = LddBertModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "lddbert"
    attribute_map = {
        "hidden_size": "dim",
        "num_attention_heads": "n_heads",
        "num_hidden_layers": "n_layers",
    }

    def __init__(
        self,
        n_layers=6,
        n_heads=12,
        dim=768,
        hidden_dim=4*768,
        activation="gelu",
        initializer_range=0.02,
        vocab_size=30522,
        max_position_embeddings=512,
        sinusoidal_pos_embds=False,
        pad_token_id=0,
        type_vocab_size=2,
        dropout=0.1,
        attention_dropout=0.1,
        qa_dropout=0.1,
        seq_classif_dropout=0.2,
        n_gru_layers=6,
        n_cnn_layers=6,
        cnn_kernel_size=5,
        **kwargs
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        self.sinusoidal_pos_embds = sinusoidal_pos_embds
        self.n_layers = n_layers
        self.n_gru_layers = n_gru_layers
        self.n_cnn_layers = n_cnn_layers
        self.cnn_kernel_size = cnn_kernel_size
        self.n_heads = n_heads
        self.dim = dim
        self.hidden_dim = hidden_dim
        self.dropout = dropout
        self.attention_dropout = attention_dropout
        self.activation = activation
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.qa_dropout = qa_dropout
        self.seq_classif_dropout = seq_classif_dropout
        super().__init__(**kwargs, pad_token_id=pad_token_id)