from transformers import PretrainedConfig

class PicoLMConfig(PretrainedConfig):
    model_type = "picolm"
    def __init__(
        self,
        vocab_size=16384,
        hidden_size=576,
        num_hidden_layers=20,
        num_attention_heads=9,
        num_key_value_heads=3,
        intermediate_size=1536,
        max_position_embeddings=2048,
        rms_norm_eps=1e-5,
        rope_theta=10000.0,
        tie_word_embeddings=True,
        **kwargs
    ):
        super().__init__(tie_word_embeddings=tie_word_embeddings, **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.num_key_value_heads = num_key_value_heads
        self.intermediate_size = intermediate_size
        self.max_position_embeddings = max_position_embeddings
        self.rms_norm_eps = rms_norm_eps
        self.rope_theta = rope_theta