from transformers import PretrainedConfig
class TinyGPTConfig(PretrainedConfig):
    model_type = "tinygpt"
    def __init__(self, vocab_size=32000, hidden_size=384, num_hidden_layers=12, num_attention_heads=8, intermediate_size=1024, max_position_embeddings=1024, rms_norm_eps=1e-6, initializer_range=0.02, **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.intermediate_size = intermediate_size
        self.max_position_embeddings = max_position_embeddings
        self.rms_norm_eps = rms_norm_eps
        self.initializer_range = initializer_range
        super().__init__(**kwargs)