# coding=utf-8
# Copyright 2023 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.
"""Pop2Piano model configuration"""

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


logger = logging.get_logger(__name__)


class Pop2PianoConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`Pop2PianoForConditionalGeneration`]. It is used
    to instantiate a Pop2PianoForConditionalGeneration 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
    Pop2Piano [sweetcocoa/pop2piano](https://huggingface.co/sweetcocoa/pop2piano) architecture.

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

    Arguments:
        vocab_size (`int`, *optional*, defaults to 2400):
            Vocabulary size of the `Pop2PianoForConditionalGeneration` model. Defines the number of different tokens
            that can be represented by the `inputs_ids` passed when calling [`Pop2PianoForConditionalGeneration`].
        composer_vocab_size (`int`, *optional*, defaults to 21):
            Denotes the number of composers.
        d_model (`int`, *optional*, defaults to 512):
            Size of the encoder layers and the pooler layer.
        d_kv (`int`, *optional*, defaults to 64):
            Size of the key, query, value projections per attention head. The `inner_dim` of the projection layer will
            be defined as `num_heads * d_kv`.
        d_ff (`int`, *optional*, defaults to 2048):
            Size of the intermediate feed forward layer in each `Pop2PianoBlock`.
        num_layers (`int`, *optional*, defaults to 6):
            Number of hidden layers in the Transformer encoder.
        num_decoder_layers (`int`, *optional*):
            Number of hidden layers in the Transformer decoder. Will use the same value as `num_layers` if not set.
        num_heads (`int`, *optional*, defaults to 8):
            Number of attention heads for each attention layer in the Transformer encoder.
        relative_attention_num_buckets (`int`, *optional*, defaults to 32):
            The number of buckets to use for each attention layer.
        relative_attention_max_distance (`int`, *optional*, defaults to 128):
            The maximum distance of the longer sequences for the bucket separation.
        dropout_rate (`float`, *optional*, defaults to 0.1):
            The ratio for all dropout layers.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-6):
            The epsilon used by the layer normalization layers.
        initializer_factor (`float`, *optional*, defaults to 1.0):
            A factor for initializing all weight matrices (should be kept to 1.0, used internally for initialization
            testing).
        feed_forward_proj (`string`, *optional*, defaults to `"gated-gelu"`):
            Type of feed forward layer to be used. Should be one of `"relu"` or `"gated-gelu"`.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        dense_act_fn (`string`, *optional*, defaults to `"relu"`):
            Type of Activation Function to be used in `Pop2PianoDenseActDense` and in `Pop2PianoDenseGatedActDense`.
    """

    model_type = "pop2piano"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=2400,
        composer_vocab_size=21,
        d_model=512,
        d_kv=64,
        d_ff=2048,
        num_layers=6,
        num_decoder_layers=None,
        num_heads=8,
        relative_attention_num_buckets=32,
        relative_attention_max_distance=128,
        dropout_rate=0.1,
        layer_norm_epsilon=1e-6,
        initializer_factor=1.0,
        feed_forward_proj="gated-gelu",  # noqa
        is_encoder_decoder=True,
        use_cache=True,
        pad_token_id=0,
        eos_token_id=1,
        dense_act_fn="relu",
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.composer_vocab_size = composer_vocab_size
        self.d_model = d_model
        self.d_kv = d_kv
        self.d_ff = d_ff
        self.num_layers = num_layers
        self.num_decoder_layers = num_decoder_layers if num_decoder_layers is not None else self.num_layers
        self.num_heads = num_heads
        self.relative_attention_num_buckets = relative_attention_num_buckets
        self.relative_attention_max_distance = relative_attention_max_distance
        self.dropout_rate = dropout_rate
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_factor = initializer_factor
        self.feed_forward_proj = feed_forward_proj
        self.use_cache = use_cache
        self.dense_act_fn = dense_act_fn
        self.is_gated_act = self.feed_forward_proj.split("-")[0] == "gated"
        self.hidden_size = self.d_model
        self.num_attention_heads = num_heads
        self.num_hidden_layers = num_layers

        super().__init__(
            pad_token_id=pad_token_id,
            eos_token_id=eos_token_id,
            is_encoder_decoder=is_encoder_decoder,
            **kwargs,
        )


__all__ = ["Pop2PianoConfig"]