from transformers.configuration_utils import PretrainedConfig


# Copied from transformers.models.m2m_100.configuration_m2m_100.M2M100Config->IndicTrans
class RotaryIndicTransConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`IT2Model`]. It is used to instantiate an
    IT2 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 IT2

    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 50265):
            Vocabulary size of the IT2 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`IT2Model`] or
        d_model (`int`, *optional*, defaults to 1024):
            Dimensionality of the layers and the pooler layer.
        encoder_layers (`int`, *optional*, defaults to 12):
            Number of encoder layers.
        decoder_layers (`int`, *optional*, defaults to 12):
            Number of decoder layers.
        encoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        decoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer decoder.
        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        encoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        activation_function (`str` or `function`, *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.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for classifier.
        max_position_embeddings (`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).
        init_std (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        encoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
            for more details.
        decoder_layerdrop (`float`, *optional*, defaults to 0.0):
            The LayerDrop probability for the decoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556)
            for more details.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
    ```"""

    model_type = "RotaryIndicTrans"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {
        "num_attention_heads": "encoder_attention_heads",
        "hidden_size": "d_model",
    }

    def __init__(
        self,
        encoder_vocab_size=None,
        decoder_vocab_size=None,
        encoder_embed_dim=512,
        decoder_embed_dim=512,
        encoder_layers=6,
        encoder_ffn_dim=2048,
        encoder_attention_heads=8,
        decoder_layers=6,
        decoder_ffn_dim=2048,
        decoder_attention_heads=8,
        encoder_layerdrop=0.00,
        decoder_layerdrop=0.00,
        use_cache=True,
        is_encoder_decoder=True,
        activation_function="relu",
        encoder_normalize_before=False,
        decoder_normalize_before=False,
        layernorm_embedding=False,
        share_decoder_input_output_embed=False,
        dropout=0.1,
        attention_dropout=0.0,
        activation_dropout=0.0,
        init_std=0.02,
        scale_embedding=True,
        decoder_start_token_id=2,
        pad_token_id=1,
        bos_token_id=0,
        eos_token_id=2,
        attn_implementation="eager",
        rope_args={"theta": 10000},
        **kwargs,
    ):
        self.encoder_vocab_size = encoder_vocab_size
        self.decoder_vocab_size = decoder_vocab_size
        self.encoder_normalize_before = encoder_normalize_before
        self.decoder_normalize_before = decoder_normalize_before
        self.layernorm_embedding = layernorm_embedding
        self.encoder_embed_dim = encoder_embed_dim
        self.decoder_embed_dim = decoder_embed_dim
        self.encoder_ffn_dim = encoder_ffn_dim
        self.encoder_layers = encoder_layers
        self.encoder_attention_heads = encoder_attention_heads
        self.decoder_ffn_dim = decoder_ffn_dim
        self.decoder_layers = decoder_layers
        self.decoder_attention_heads = decoder_attention_heads
        self.dropout = dropout
        self.attention_dropout = attention_dropout
        self.activation_dropout = activation_dropout
        self.activation_function = activation_function
        self.init_std = init_std
        self.encoder_layerdrop = encoder_layerdrop
        self.decoder_layerdrop = decoder_layerdrop
        self.use_cache = use_cache
        self.rope_args = rope_args
        self.num_hidden_layers = encoder_layers
        self.scale_embedding = scale_embedding
        self.share_decoder_input_output_embed = share_decoder_input_output_embed
        self.attn_implementation = attn_implementation

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