from __future__ import annotations

from transformers import PretrainedConfig


class TalkieConfig(PretrainedConfig):
    model_type = "talkie"

    def __init__(
        self,
        vocab_size: int = 65536,
        n_layer: int = 40,
        n_head: int = 40,
        n_embd: int = 5120,
        head_dim: int = 128,
        max_position_embeddings: int = 2048,
        rope_base: int = 1_000_000,
        logit_scale: float = 1.0,
        use_cache: bool = True,
        tie_word_embeddings: bool = False,
        bos_token_id: int | None = None,
        eos_token_id: int | list[int] = 65535,
        pad_token_id: int | None = None,
        **kwargs,
    ):
        super().__init__(
            bos_token_id=bos_token_id,
            eos_token_id=eos_token_id,
            pad_token_id=pad_token_id,
            tie_word_embeddings=tie_word_embeddings,
            **kwargs,
        )
        self.vocab_size = vocab_size
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_embd = n_embd
        self.head_dim = head_dim
        self.max_position_embeddings = max_position_embeddings
        self.rope_base = rope_base
        self.logit_scale = logit_scale
        self.use_cache = use_cache

        # Common Transformers aliases used by generation/cache helpers.
        self.hidden_size = n_embd
        self.num_hidden_layers = n_layer
        self.num_attention_heads = n_head