from transformers import PretrainedConfig, GPT2Config
from typing import List


class GPTOptimConfig(GPT2Config):
    model_type = "gpt_optimized"

    def __init__(
        self,
        block_size: int = 1024, # max sequence length
        vocab_size: int = 50257, # number of tokens: 50,000 BPE merges + 256 bytes tokens + 1 <|endoftext|> token
        n_layer: int = 16, # number of layers
        n_head: int = 16, # number of heads
        n_embd: int = 1024, # embedding dimension
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.block_size = block_size
        self.vocab_size = vocab_size
        self.n_layer = n_layer
        self.n_head = n_head
        self.n_embd = n_embd