# coding=utf-8
# Copyright 2022 IDEA-CCNL 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.
""" Della model configuration """

from transformers.configuration_utils import PretrainedConfig


Della_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "Della-226M-base": "https://huggingface.co/IDEA-CCNL/Randeng-DELLA-226M-Chinese/resolve/main/config.json"
}


class DellaModelConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`~DellaModel`].
    It is used to instantiate an DellaModel 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 DellaModel [Randeng-DELLA-226M-Chinese](https://huggingface.co/IDEA-CCNL/Randeng-DELLA-226M-Chinese) 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 Della model. Defines the number of different
            tokens that can be represented by the
            `inputs_ids` passed when calling [`~DellaModel`] or
            [`~TFDellaModel`].
        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 [`~DellaModel`] or
            [`~TFDellaModel`].
        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`.

"""
    model_type = "DellaModel"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "hidden_size": "n_embd",
        "max_position_embeddings": "n_positions",
        "num_attention_heads": "n_head",
        "num_hidden_layers": "n_layer",
    }

    def __init__(
        self,
        vocab_size=50257,
        n_positions=1024,
        n_embd=768,
        n_layer=12,
        n_head=12,
        n_inner=None,
        activation_function="gelu_new",
        resid_pdrop=0.1,
        embd_pdrop=0.1,
        attn_pdrop=0.1,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        scale_attn_weights=True,
        use_cache=True,
        scale_attn_by_inverse_layer_idx=False,
        reorder_and_upcast_attn=False,
        bos_token_id=21128,
        eos_token_id=21129,
        pad_token_id=0,
        CVAE=False,
        latent_dim=256,
        **kwargs,
    ):
        self.vocab_size = vocab_size
        self.n_positions = n_positions
        self.n_embd = n_embd
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_inner = n_inner
        self.activation_function = activation_function
        self.resid_pdrop = resid_pdrop
        self.embd_pdrop = embd_pdrop
        self.attn_pdrop = attn_pdrop
        self.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range

        self.scale_attn_weights = scale_attn_weights
        self.use_cache = use_cache
        self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx
        self.reorder_and_upcast_attn = reorder_and_upcast_attn

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.pad_token_id = pad_token_id
        self.CVAE = CVAE
        self.latent_dim = latent_dim
        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, **kwargs)