nemo_automodel.components.models.baichuan.configuration

class nemo_automodel.components.models.baichuan.configuration.BaichuanConfig(
    vocab_size = 125696,
    hidden_size = 4096,
    intermediate_size = 11008,
    num_hidden_layers = 32,
    num_attention_heads = 32,
    hidden_act = 'silu',
    max_position_embeddings = 4096,
    initializer_range = 0.02,
    rms_norm_eps = 1e-06,
    use_cache = True,
    pad_token_id = 0,
    bos_token_id = 1,
    eos_token_id = 2,
    tie_word_embeddings = False,
    z_loss_weight = 0,
    kwargs = {}
)