# coding=utf-8
# Copyright 2022 {{cookiecutter.authors}} and The HuggingFace Inc. team. 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.
""" {{cookiecutter.modelname}} model configuration """

from ...configuration_utils import PretrainedConfig
from ...utils import logging


logger = logging.get_logger(__name__)

{{cookiecutter.uppercase_modelname}}_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "{{cookiecutter.checkpoint_identifier}}": "https://huggingface.co/{{cookiecutter.checkpoint_identifier}}/resolve/main/config.json",
    # See all {{cookiecutter.modelname}} models at https://huggingface.co/models?filter={{cookiecutter.lowercase_modelname}}
}


class {{cookiecutter.camelcase_modelname}}Config(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`~{{cookiecutter.camelcase_modelname}}Model`].
    It is used to instantiate an {{cookiecutter.modelname}} 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 {{cookiecutter.modelname}} [{{cookiecutter.checkpoint_identifier}}](https://huggingface.co/{{cookiecutter.checkpoint_identifier}}) architecture.

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


    Args:
        {% if cookiecutter.is_encoder_decoder_model == "False" -%}
        vocab_size (`int`, *optional*, defaults to 30522):
            Vocabulary size of the {{cookiecutter.modelname}} model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`~{{cookiecutter.camelcase_modelname}}Model`] or
            [`~TF{{cookiecutter.camelcase_modelname}}Model`].
        hidden_size (`int`, *optional*, defaults to 768):
            Dimension 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):
            Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler.
            If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported.
        hidden_dropout_prob (`float`, *optional*, defaults to 0.1):
            The dropout probabilitiy 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 [`~{{cookiecutter.camelcase_modelname}}Model`] or
            [`~TF{{cookiecutter.camelcase_modelname}}Model`].
        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.
        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`.
        {% else -%}
        vocab_size (`int`, *optional*, defaults to 50265):
            Vocabulary size of the {{cookiecutter.modelname}} model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`~{{cookiecutter.camelcase_modelname}}Model`] or
            [`~TF{{cookiecutter.camelcase_modelname}}Model`].
        d_model (`int`, *optional*, defaults to 1024):
            Dimension of the layers and the pooler layer.
        encoder_layers (`int`, *optional*, defaults to 12):
            Number of encoder layers.
        decoder_layers (`int`, *optional*, defaults to 12):
            Number of decoder layers.
        encoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        decoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer decoder.
        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimension of the "intermediate" (often named feed-forward) layer in decoder.
        encoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimension of the "intermediate" (often named feed-forward) layer in decoder.
        activation_function (`str` or `function`, *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.
        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 0.0):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for classifier.
        max_position_embeddings (`int`, *optional*, defaults to 1024):
            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).
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the encoder. See the [LayerDrop paper](see
            https://arxiv.org/abs/1909.11556) for more details.
        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the decoder. See the [LayerDrop paper](see
            https://arxiv.org/abs/1909.11556) for more details.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        {% endif -%}

    Example:

    ```python
    >>> from transformers import {{cookiecutter.camelcase_modelname}}Model, {{cookiecutter.camelcase_modelname}}Config

    >>> # Initializing a {{cookiecutter.modelname}} {{cookiecutter.checkpoint_identifier}} style configuration
    >>> configuration = {{cookiecutter.camelcase_modelname}}Config()

    >>> # Initializing a model from the {{cookiecutter.checkpoint_identifier}} style configuration
    >>> model = {{cookiecutter.camelcase_modelname}}Model(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```
"""
    model_type = "{{cookiecutter.lowercase_modelname}}"
    {% if cookiecutter.is_encoder_decoder_model == "False" -%}
    {% else -%}
    keys_to_ignore_at_inference = ["past_key_values"]
    {% endif -%}
    
    {% if cookiecutter.is_encoder_decoder_model == "False" %}
    {%- else %}
    attribute_map = {
        "num_attention_heads": "encoder_attention_heads",
        "hidden_size": "d_model"
    }

    {%- endif %}

    def __init__(
        self,
        {% if cookiecutter.is_encoder_decoder_model == "False" -%}
        vocab_size=30522,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        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-12,
        use_cache=True,
        {% else -%}
        vocab_size=50265,
        max_position_embeddings=1024,
        encoder_layers=12,
        encoder_ffn_dim=4096,
        encoder_attention_heads=16,
        decoder_layers=12,
        decoder_ffn_dim=4096,
        decoder_attention_heads=16,
        encoder_layerdrop=0.0,
        decoder_layerdrop=0.0,
        use_cache=True,
        is_encoder_decoder=True,
        activation_function="gelu",
        d_model=1024,
        dropout=0.1,
        attention_dropout=0.0,
        activation_dropout=0.0,
        init_std=0.02,
        decoder_start_token_id=2,
        classifier_dropout=0.0,
        scale_embedding=False,
        {% endif -%}
        pad_token_id=1,
        bos_token_id=0,
        eos_token_id=2,
        **kwargs
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_position_embeddings
        {% if cookiecutter.is_encoder_decoder_model == "False" -%}
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.initializer_range = initializer_range
        self.type_vocab_size = type_vocab_size
        self.layer_norm_eps = layer_norm_eps
        self.use_cache = use_cache
        {% else -%}
        self.d_model = d_model
        self.encoder_ffn_dim = encoder_ffn_dim
        self.encoder_layers = encoder_layers
        self.encoder_attention_heads = encoder_attention_heads
        self.decoder_ffn_dim = decoder_ffn_dim
        self.decoder_layers = decoder_layers
        self.decoder_attention_heads = decoder_attention_heads
        self.dropout = dropout
        self.attention_dropout = attention_dropout
        self.activation_dropout = activation_dropout
        self.activation_function = activation_function
        self.init_std = init_std
        self.encoder_layerdrop = encoder_layerdrop
        self.decoder_layerdrop = decoder_layerdrop
        self.classifier_dropout = classifier_dropout
        self.use_cache = use_cache
        self.num_hidden_layers = encoder_layers
        self.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True

        {% endif -%}
        super().__init__(
            pad_token_id=pad_token_id,
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            {% if cookiecutter.is_encoder_decoder_model == "False" -%}
            {% else -%}
            is_encoder_decoder=is_encoder_decoder,
            decoder_start_token_id=decoder_start_token_id,
            {% endif -%}
            **kwargs
        )