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

logger = logging.get_logger(__name__)

CYBERAI_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "CyberCapstone/CyberAI": "https://huggingface.co/CyberCapstone/CyberAI/blob/main/config.json"
}

class CyberAIConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`CyberAIModel`]. It is used to instantiate a CyberAI
    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 CyberCapstone/CyberAI 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 65024):
            Vocabulary size of the CyberAI model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`CyberAIModel`].
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer decoder.
        num_attention_heads (`int`, *optional*, defaults to 64):
            Number of attention heads for each attention layer in the Transformer encoder.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-05):
            The epsilon used by 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.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether the model should return the last key/values attentions (not used by all models). Only relevant if
            `config.is_decoder=True`.
        hidden_dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for MLP layers.
        attention_dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for attention layers.
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with.
        pad_token_id (`int`, *optional*, defaults to 0):
            Padding token id.
        bos_token_id (`int`, *optional*, defaults to 1):
            Beginning of stream token id.
        eos_token_id (`int`, *optional*, defaults to 2):
            End of stream token id.
        attention_bias (`bool`, defaults to `True`, *optional*):
            Whether to use a bias in the query, key, value, and output projection layers during self-attention.
    Example:
    ```python
    >>> from transformers import CyberAIModel, CyberAIConfig
    >>> # Initializing a CyberCapstone/CyberAI configuration
    >>> configuration = CyberAIConfig()
    >>> # Initializing a model from the configuration
    >>> model = CyberAIModel(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "cyberai"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
        self,
        vocab_size=65024,
        hidden_size=4096,
        num_hidden_layers=32,
        num_attention_heads=64,
        layer_norm_epsilon=1e-5,
        initializer_range=0.02,
        use_cache=True,
        hidden_dropout=0.1,
        attention_dropout=0.1,
        max_position_embeddings=2048,
        pad_token_id=0,
        bos_token_id=1,
        eos_token_id=2,
        attention_bias=True,
        **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.layer_norm_epsilon = layer_norm_epsilon
        self.initializer_range = initializer_range
        self.use_cache = use_cache
        self.hidden_dropout = hidden_dropout
        self.attention_dropout = attention_dropout
        self.max_position_embeddings = max_position_embeddings
        self.pad_token_id = pad_token_id
        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.attention_bias = attention_bias

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

# Example usage
if __name__ == "__main__":
    config = CyberAIConfig()
    print(config)