nemo_automodel.components.models.hy_v3.config

class nemo_automodel.components.models.hy_v3.config.HYV3Config(
    vocab_size: int = 129280,
    hidden_size: int = 4096,
    intermediate_size: int = 1536,
    moe_intermediate_size: int = 1536,
    num_hidden_layers: int = 80,
    num_attention_heads: int = 64,
    num_key_value_heads: int = 8,
    head_dim: int = 128,
    num_experts: int = 192,
    num_shared_experts: int = 1,
    num_experts_per_tok: int = 8,
    router_scaling_factor: float = 1.0,
    route_norm: bool = False,
    moe_router_enable_expert_bias: bool = True,
    first_k_dense_replace: int = 1,
    max_position_embeddings: int = 262144,
    rope_theta: float = 11158840.0,
    rope_scaling: dict | None = None,
    rms_norm_eps: float = 1e-06,
    attention_bias: bool = False,
    hidden_act: str = 'silu',
    use_cache: bool = True,
    pad_token_id: int | None = None,
    bos_token_id: int = 1,
    eos_token_id: int = 2,
    tie_word_embeddings: bool = False,
    torch_dtype: str = 'bfloat16',
    kwargs = {}
)