DeepseekV3/inference/configs/config_236B.json

{
    "vocab_size": 102400,
    "dim": 5120,
    "inter_dim": 12288,
    "moe_inter_dim": 1536,
    "n_layers": 60,
    "n_dense_layers": 1,
    "n_heads": 128,
    "n_routed_experts": 160,
    "n_shared_experts": 2,
    "n_activated_experts": 6,
    "n_expert_groups": 8,
    "n_limited_groups": 3,
    "route_scale": 16.0,
    "q_lora_rank": 1536,
    "kv_lora_rank": 512,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "v_head_dim": 128
}