# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved.
#
# 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.
"""MPNet model configuration"""
from __future__ import annotations

from paddlenlp.transformers.configuration_utils import PretrainedConfig

__all__ = [
    "MPNET_PRETRAINED_INIT_CONFIGURATION",
    "MPNetConfig",
]

MPNET_PRETRAINED_INIT_CONFIGURATION = {}


class MPNetConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`MPNetModel`]. It is used to
    instantiate a MPNet 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 MPNet.

    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 30527):
            Vocabulary size of the MPNet model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`MPNetModel`].
        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 514):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case.
        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-5):
            The epsilon used by the layer normalization layers.
        relative_attention_num_buckets (`int`, *optional*, defaults to 32):
            The number of buckets to use for each attention layer.

    Examples:

    ```python
    >>> from paddlenlp.transformers import MPNetModel, MPNetConfig

    >>> # Initializing a MPNet mpnet-base style configuration
    >>> configuration = MPNetConfig()

    >>> # Initializing a model from the MPNet mpnet-base style configuration
    >>> model = MPNetModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "mpnet"
    attribute_map = {
        "num_classes": "num_labels",
    }

    def __init__(
        self,
        vocab_size: int = 30527,
        hidden_size: int = 768,
        num_hidden_layers: int = 12,
        num_attention_heads: int = 12,
        intermediate_size: int = 3072,
        hidden_act: str = "gelu",
        hidden_dropout_prob: float = 0.1,
        attention_probs_dropout_prob: float = 0.1,
        max_position_embeddings: int = 514,
        initializer_range: float = 0.02,
        layer_norm_eps: float = 1e-5,
        relative_attention_num_buckets: int = 32,
        pad_token_id: int = 1,
        bos_token_id: int = 0,
        eos_token_id: int = 2,
        **kwargs
    ):
        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_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.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.relative_attention_num_buckets = relative_attention_num_buckets