{
  "model_type": "qwen3_5_moe",
  "hidden": 2048,
  "n_layers": 40,
  "n_active": 40,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "num_experts": 256,
  "topk": 8,
  "moe_inter": 512,
  "shared_inter": 512,
  "rms_eps": 1e-06,
  "ebits": 4,
  "scoring_func": "softmax",
  "n_group": 1,
  "topk_group": 1,
  "norm_topk_prob": false,
  "attn_output_gate": true,
  "rope_theta": 10000000.0,
  "mrope_section": [
    11,
    11,
    10
  ],
  "partial_rotary_factor": 0.25,
  "q_heads": 16,
  "kv_heads": 2,
  "q_head_dim": 512,
  "k_head_dim": 256,
  "v_head_dim": 256,
  "o_in": 4096,
  "qk_rope_head_dim": 256,
  "expert_gs": 64,
  "head_dim": 256,
  "rope_dim": 256,
  "dn_vheads": 32,
  "dn_kheads": 16,
  "dn_kdim": 128,
  "dn_vdim": 128,
  "dn_convk": 4,
  "dn_conv_dim": 8192
}