DeepseekV3/inference/configs/config_16B.json

{
    "vocab_size": 102400,
    "dim": 2048,
    "inter_dim": 10944,
    "moe_inter_dim": 1408,
    "n_layers": 27,
    "n_dense_layers": 1,
    "n_heads": 16,
    "n_routed_experts": 64,
    "n_shared_experts": 2,
    "n_activated_experts": 6,
    "route_scale": 1.0,
    "q_lora_rank": 0,
    "kv_lora_rank": 512,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "v_head_dim": 128,
    "mscale": 0.707
}