models/config.py

from transformers import PretrainedConfig


class TinyGPTConfig(PretrainedConfig):
    model_type = "tinygpt"

    def __init__(
        self,
        vocab_size=50257,
        embed_dim=256,
        max_seq_len=128,
        num_layers=4,
        **kwargs,
    ):
        super().__init__(**kwargs)
        self.vocab_size = vocab_size
        self.embed_dim = embed_dim
        self.max_seq_len = max_seq_len
        self.num_layers = num_layers
        self.num_hidden_layers = num_layers


TinyGPTConfig.register_for_auto_class("AutoConfig")