"""LoRDCoder configuration class, based on GPT configuration class.

License: Apache-2.0
"""
from transformers.configuration_utils import PretrainedConfig

class LoRDCoderConfig(PretrainedConfig):
    """
    This is the configuration class to store the configuration of a [`LoRDCoderModel`]. It is used to instantiate a
    LoRDCoder model according to the specified arguments, defining the model 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 50257):
            Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`LoRDCoderModel`].
        n_positions (`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).
        n_embd (`int`, *optional*, defaults to 768):
            Dimensionality of the embeddings and hidden states.
        n_layer (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        n_head (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        n_inner (`int`, *optional*, defaults to None):
            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
        activation_function (`str`, *optional*, defaults to `"gelu_pytorch_tanh"`):
            Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new",
            "gelu_pytorch_tanh"]`.
        resid_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        embd_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the embeddings.
        attn_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        scale_attn_weights (`bool`, *optional*, defaults to `True`):
            Scale attention weights by dividing by sqrt(hidden_size)..
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        attention_softmax_in_fp32 (`bool`, *optional*, defaults to `True`):
            Whether to call the fused softmax in float32.
        scale_attention_softmax_in_fp32 (`bool`, *optional*, defaults to `True`):
            Whether to scale the attention softmax in float32.
        attention_type (`bool`, *optional*, defaults to `True`):
            Whether to use Multi-Query Attion (`True`) or Multi-Head Attention (`False`).
    Example:

    ```python
    >>> from transformers import LoRDCoderConfig, LoRDCoderModel

    >>> # Initializing a LoRDCoder configuration
    >>> configuration = LoRDCoderConfig()

    >>> # Initializing a model (with random weights) from the configuration
    >>> model = LoRDCoderModel(configuration)

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

    model_type = "lordcoder"
    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_pytorch_tanh",
        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,
        bos_token_id=50256,
        eos_token_id=50256,
        attention_softmax_in_fp32=True,
        scale_attention_softmax_in_fp32=True,
        multi_query=True,
        gate_dim=4096,
        **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.attention_softmax_in_fp32 = attention_softmax_in_fp32
        self.scale_attention_softmax_in_fp32 = scale_attention_softmax_in_fp32
        self.multi_query = multi_query
        self.gate_dim = gate_dim

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id

        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)