# coding=utf-8
# Copyright Microsoft Research 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.

from collections import OrderedDict
from typing import Mapping

from transformers.configuration_utils import PretrainedConfig
from transformers.onnx import OnnxConfig


BERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/config.json",
    "bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/config.json",
    "bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/config.json",
    "bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/config.json",
    "bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/config.json",
    "bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/config.json",
    "bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/config.json",
    "bert-base-german-cased": "https://huggingface.co/bert-base-german-cased/resolve/main/config.json",
    "bert-large-uncased-whole-word-masking": "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/config.json",
    "bert-large-cased-whole-word-masking": "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/config.json",
    "bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/config.json",
    "bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/config.json",
    "bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/config.json",
    "bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/config.json",
    "bert-base-german-dbmdz-uncased": "https://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/config.json",
    "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/config.json",
    "cl-tohoku/bert-base-japanese-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/config.json",
    "cl-tohoku/bert-base-japanese-char": "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/config.json",
    "cl-tohoku/bert-base-japanese-char-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/config.json",
    "TurkuNLP/bert-base-finnish-cased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/config.json",
    "TurkuNLP/bert-base-finnish-uncased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/config.json",
    "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/config.json",
    # See all BERT models at https://huggingface.co/models?filter=bert
}


class BertConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`BertModel`] or a
    [`TFBertModel`]. It is used to instantiate a BERT 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 BERT [bert-base-uncased](https://huggingface.co/bert-base-uncased) 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 BERT model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`BertModel`] or
            [`TFBertModel`].
        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 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 [`BertModel`] or
            [`TFBertModel`].
        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.
        position_embedding_type (`str`, *optional*, defaults to `"absolute"`):
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`,
            `"relative_key_query"`. For positional embeddings use `"absolute"`. For more information on
            `"relative_key"`, please refer to [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155). For more information on `"relative_key_query"`, please refer to
            *Method 4* in [Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        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`.
        classifier_dropout (`float`, *optional*):
            The dropout ratio for the classification head.

    Examples:

    ```python
    >>> from transformers import BertModel, BertConfig

    >>> # Initializing a BERT bert-base-uncased style configuration
    >>> configuration = BertConfig()

    >>> # Initializing a model from the bert-base-uncased style configuration
    >>> model = BertModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "bert"

    def __init__(
        self,
        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,
        pad_token_id=0,
        position_embedding_type="absolute",
        use_cache=True,
        classifier_dropout=None,
        token_keep_rate=1,
        token_keep_strategy='cls_attn',
        token_drop_loc=[9],
        **kwargs
    ):
        super().__init__(pad_token_id=pad_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.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.classifier_dropout = classifier_dropout
        self.token_keep_rate = token_keep_rate
        self.token_keep_strategy = token_keep_strategy
        self.token_drop_loc = token_drop_loc


class BertOnnxConfig(OnnxConfig):
    @property
    def inputs(self) -> Mapping[str, Mapping[int, str]]:
        return OrderedDict(
            [
                ("input_ids", {0: "batch", 1: "sequence"}),
                ("attention_mask", {0: "batch", 1: "sequence"}),
                ("token_type_ids", {0: "batch", 1: "sequence"}),
            ]
        )


BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "microsoft/beit-base-patch16-224-in22k": "https://huggingface.co/microsoft/beit-base-patch16-224-in22k/resolve/main/config.json",
    # See all BEiT models at https://huggingface.co/models?filter=beit
}


class BeitConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`BeitModel`]. It is used to
    instantiate an BEiT 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 BEiT
    [microsoft/beit-base-patch16-224-in22k](https://huggingface.co/microsoft/beit-base-patch16-224-in22k)
    architecture.

    Args:
        vocab_size (`int`, *optional*, defaults to 8092):
            Vocabulary size of the BEiT model. Defines the number of different image tokens that can be used during
            pre-training.
        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" (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 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.
        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.
        image_size (`int`, *optional*, defaults to `224`):
            The size (resolution) of each image.
        patch_size (`int`, *optional*, defaults to `16`):
            The size (resolution) of each patch.
        num_channels (`int`, *optional*, defaults to `3`):
            The number of input channels.
        use_mask_token (`bool`, *optional*, defaults to `False`):
            Whether to use a mask token for masked image modeling.
        use_absolute_position_embeddings (`bool`, *optional*, defaults to `False`):
            Whether to use BERT-style absolute position embeddings.
        use_relative_position_bias (`bool`, *optional*, defaults to `False`):
            Whether to use T5-style relative position embeddings in the self-attention layers.
        use_shared_relative_position_bias (`bool`, *optional*, defaults to `False`):
            Whether to use the same relative position embeddings across all self-attention layers of the Transformer.
        layer_scale_init_value (`float`, *optional*, defaults to 0.1):
            Scale to use in the self-attention layers. 0.1 for base, 1e-5 for large. Set 0 to disable layer scale.
        drop_path_rate (`float`, *optional*, defaults to 0.1):
            Stochastic depth rate per sample (when applied in the main path of residual layers).
        use_mean_pooling (`bool`, *optional*, defaults to `True`):
            Whether to mean pool the final hidden states of the patches instead of using the final hidden state of the
            CLS token, before applying the classification head.
        out_indices (`List[int]`, *optional*, defaults to `[3, 5, 7, 11]`):
            Indices of the feature maps to use for semantic segmentation.
        pool_scales (`Tuple[int]`, *optional*, defaults to `[1, 2, 3, 6]`):
            Pooling scales used in Pooling Pyramid Module applied on the last feature map.
        use_auxiliary_head (`bool`, *optional*, defaults to `True`):
            Whether to use an auxiliary head during training.
        auxiliary_loss_weight (`float`, *optional*, defaults to 0.4):
            Weight of the cross-entropy loss of the auxiliary head.
        auxiliary_channels (`int`, *optional*, defaults to 256):
            Number of channels to use in the auxiliary head.
        auxiliary_num_convs (`int`, *optional*, defaults to 1):
            Number of convolutional layers to use in the auxiliary head.
        auxiliary_concat_input (`bool`, *optional*, defaults to `False`):
            Whether to concatenate the output of the auxiliary head with the input before the classification layer.
        semantic_loss_ignore_index (`int`, *optional*, defaults to 255):
            The index that is ignored by the loss function of the semantic segmentation model.

    Example:

    ```python
    >>> from transformers import BeitModel, BeitConfig

    >>> # Initializing a BEiT beit-base-patch16-224-in22k style configuration
    >>> configuration = BeitConfig()

    >>> # Initializing a model from the beit-base-patch16-224-in22k style configuration
    >>> model = BeitModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""
    model_type = "beit"

    def __init__(
        self,
        vocab_size=8192,
        hidden_size=768,
        num_hidden_layers=12,
        num_attention_heads=12,
        intermediate_size=3072,
        hidden_act="gelu",
        hidden_dropout_prob=0.0,
        attention_probs_dropout_prob=0.0,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        is_encoder_decoder=False,
        image_size=224,
        patch_size=16,
        num_channels=3,
        use_mask_token=False,
        use_absolute_position_embeddings=False,
        use_relative_position_bias=False,
        use_shared_relative_position_bias=False,
        layer_scale_init_value=0.1,
        drop_path_rate=0.1,
        use_mean_pooling=True,
        out_indices=[3, 5, 7, 11],
        pool_scales=[1, 2, 3, 6],
        use_auxiliary_head=True,
        auxiliary_loss_weight=0.4,
        auxiliary_channels=256,
        auxiliary_num_convs=1,
        auxiliary_concat_input=False,
        semantic_loss_ignore_index=255,
        token_keep_rate=1,
        token_keep_strategy='cls_attn',
        token_drop_loc=[3, 6, 9],
        sparse_random_attn=None,
        sparse_local_attn=1,
        attn_block_size=1,
        num_cls_tokens=1,
        token_3d_order='none',
        **kwargs
    ):
        super().__init__(**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.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.layer_norm_eps = layer_norm_eps

        self.image_size = image_size
        self.patch_size = patch_size
        self.num_channels = num_channels
        self.use_mask_token = use_mask_token
        self.use_absolute_position_embeddings = use_absolute_position_embeddings
        self.use_relative_position_bias = use_relative_position_bias
        self.use_shared_relative_position_bias = use_shared_relative_position_bias
        self.layer_scale_init_value = layer_scale_init_value
        self.drop_path_rate = drop_path_rate
        self.use_mean_pooling = use_mean_pooling
        # decode head attributes (semantic segmentation)
        self.out_indices = out_indices
        self.pool_scales = pool_scales
        # auxiliary head attributes (semantic segmentation)
        self.use_auxiliary_head = use_auxiliary_head
        self.auxiliary_loss_weight = auxiliary_loss_weight
        self.auxiliary_channels = auxiliary_channels
        self.auxiliary_num_convs = auxiliary_num_convs
        self.auxiliary_concat_input = auxiliary_concat_input
        self.semantic_loss_ignore_index = semantic_loss_ignore_index

        # node sparsification
        self.token_keep_rate = token_keep_rate
        self.token_keep_strategy = token_keep_strategy
        self.token_drop_loc = token_drop_loc
        # edge sparsification
        self.sparse_random_attn = sparse_random_attn
        self.sparse_local_attn = sparse_local_attn
        self.attn_block_size = attn_block_size
        self.num_cls_tokens = num_cls_tokens
        # token order
        self.token_3d_order = token_3d_order