{
  "enabled": true,
  "cache_path": "/Users/tim/.omlx/models/.oqe_imatrix/Qwen3.8-Flash-Next-Uncensored-9cb1917c3ea2-s128-l512.npz",
  "cache_reused": false,
  "entry_count": 937,
  "calib_dataset": "oqe_code_multilingual",
  "collection": {
    "dataset": "oqe_code_multilingual",
    "requested_samples": 128,
    "seq_length": 512,
    "adaptive": true,
    "adaptive_step_samples": 128,
    "adaptive_max_samples": 1024,
    "available_samples": 1024,
    "micro_batch_size": 8,
    "micro_batches": 128,
    "batch_plan": {
      "micro_batch_size": 8,
      "estimated_sample_bytes": 52428800,
      "capture_budget_bytes": 447505614,
      "system_available_bytes": 116726628352,
      "metal_available_bytes": 130562220814,
      "live_available_bytes": 116726628352,
      "model_bytes": 71976066934,
      "remaining_available_bytes": 44750561418,
      "fits_one_sample": true,
      "hidden_size": 2560,
      "num_experts": 512,
      "top_k": 10,
      "gemma4_state_bytes": 0,
      "num_hidden_layers": 48,
      "num_kv_shared_layers": 0,
      "per_layer_input_size": 0
    },
    "processed_samples": 1024,
    "model_class": "mlx_vlm.models.qwen4_exp.qwen4_exp.Model",
    "layer_model_class": "mlx_vlm.models.qwen4_exp.language.Qwen4ExpModel",
    "layer_model_type": "qwen4_exp_text",
    "layer_count": 48,
    "layer_state_kind": "qwen4_exp",
    "successful_layer_forwards": 6144,
    "skipped_layer_forwards": 0,
    "mtp_head_forwards": 128,
    "installed_modules": 1050,
    "capture_module_classes": {
      "Linear": 159,
      "QuantizedLinear": 744,
      "QuantizedSwitchLinear": 147
    },
    "switch_capture_modules": 147,
    "requires_expert_counts": true,
    "coverage_sufficient": false,
    "collection_sufficient": false,
    "coverage": {
      "has_expert_counts": true,
      "expert_modules": 147,
      "total_experts": 75264,
      "active_experts": 75243,
      "zero_count_experts": 21,
      "active_ratio": 0.9997209821428571,
      "min_count": 0,
      "p05_count": 1805.0,
      "p10_count": 2781.3,
      "median_count": 8252.0,
      "max_count": 172934,
      "min_required_count": 16,
      "required_percentile": 5
    },
    "rounds": [
      {
        "processed_samples": 128,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75225,
          "zero_count_experts": 39,
          "active_ratio": 0.9994818239795918,
          "min_count": 0,
          "p05_count": 215.0,
          "p10_count": 339.0,
          "median_count": 1039.0,
          "max_count": 20672,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 256,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75240,
          "zero_count_experts": 24,
          "active_ratio": 0.9996811224489796,
          "min_count": 0,
          "p05_count": 439.0,
          "p10_count": 682.0,
          "median_count": 2064.0,
          "max_count": 42223,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 384,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 691.0,
          "p10_count": 1046.0,
          "median_count": 3108.0,
          "max_count": 64161,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 512,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 908.0,
          "p10_count": 1373.0,
          "median_count": 4121.0,
          "max_count": 85280,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 640,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 1105.0,
          "p10_count": 1716.0,
          "median_count": 5155.0,
          "max_count": 106967,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 768,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 1369.0,
          "p10_count": 2069.3,
          "median_count": 6195.0,
          "max_count": 129533,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 896,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 1586.0,
          "p10_count": 2417.0,
          "median_count": 7238.0,
          "max_count": 150988,
          "min_required_count": 16,
          "required_percentile": 5
        }
      },
      {
        "processed_samples": 1024,
        "coverage_sufficient": false,
        "collection_sufficient": false,
        "coverage": {
          "has_expert_counts": true,
          "expert_modules": 147,
          "total_experts": 75264,
          "active_experts": 75243,
          "zero_count_experts": 21,
          "active_ratio": 0.9997209821428571,
          "min_count": 0,
          "p05_count": 1805.0,
          "p10_count": 2781.3,
          "median_count": 8252.0,
          "max_count": 172934,
          "min_required_count": 16,
          "required_percentile": 5
        }
      }
    ]
  },
  "expert_coverage": {
    "has_expert_counts": true,
    "expert_modules": 147,
    "total_experts": 75264,
    "active_experts": 75243,
    "zero_count_experts": 21,
    "active_ratio": 0.9997209821428571,
    "min_count": 0,
    "p05_count": 1805.0,
    "p10_count": 2781.3,
    "median_count": 8252.0,
    "max_count": 172934,
    "min_required_count": 16,
    "required_percentile": 5
  },
  "applied": [
    "language_model.model.layers.0.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.0.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.0.linear_attn.in_proj_a",
    "language_model.model.layers.0.linear_attn.in_proj_b",
    "language_model.model.layers.0.linear_attn.in_proj_qkv",
    "language_model.model.layers.0.linear_attn.in_proj_z",
    "language_model.model.layers.0.linear_attn.out_proj",
    "language_model.model.layers.0.mlp.shared_expert.down_proj",
    "language_model.model.layers.0.mlp.shared_expert.gate_proj",
    "language_model.model.layers.0.mlp.shared_expert.up_proj",
    "language_model.model.layers.0.mlp.shared_expert_gate",
    "language_model.model.layers.0.mlp.switch_mlp.down_proj",
    "language_model.model.layers.0.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.0.mlp.switch_mlp.up_proj",
    "language_model.model.layers.0.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.1.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.1.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.1.linear_attn.in_proj_a",
    "language_model.model.layers.1.linear_attn.in_proj_b",
    "language_model.model.layers.1.linear_attn.in_proj_qkv",
    "language_model.model.layers.1.linear_attn.in_proj_z",
    "language_model.model.layers.1.linear_attn.out_proj",
    "language_model.model.layers.1.mlp.shared_expert.down_proj",
    "language_model.model.layers.1.mlp.shared_expert.gate_proj",
    "language_model.model.layers.1.mlp.shared_expert.up_proj",
    "language_model.model.layers.1.mlp.shared_expert_gate",
    "language_model.model.layers.1.mlp.switch_mlp.down_proj",
    "language_model.model.layers.1.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.1.mlp.switch_mlp.up_proj",
    "language_model.model.layers.1.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.1.ple.key_proj",
    "language_model.model.layers.1.ple.value_proj",
    "language_model.model.layers.10.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.10.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.10.linear_attn.in_proj_a",
    "language_model.model.layers.10.linear_attn.in_proj_b",
    "language_model.model.layers.10.linear_attn.in_proj_qkv",
    "language_model.model.layers.10.linear_attn.in_proj_z",
    "language_model.model.layers.10.linear_attn.out_proj",
    "language_model.model.layers.10.mlp.shared_expert.down_proj",
    "language_model.model.layers.10.mlp.shared_expert.gate_proj",
    "language_model.model.layers.10.mlp.shared_expert.up_proj",
    "language_model.model.layers.10.mlp.shared_expert_gate",
    "language_model.model.layers.10.mlp.switch_mlp.down_proj",
    "language_model.model.layers.10.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.10.mlp.switch_mlp.up_proj",
    "language_model.model.layers.10.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.11.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.11.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.11.mlp.shared_expert.down_proj",
    "language_model.model.layers.11.mlp.shared_expert.gate_proj",
    "language_model.model.layers.11.mlp.shared_expert.up_proj",
    "language_model.model.layers.11.mlp.shared_expert_gate",
    "language_model.model.layers.11.mlp.switch_mlp.down_proj",
    "language_model.model.layers.11.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.11.mlp.switch_mlp.up_proj",
    "language_model.model.layers.11.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.11.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.11.self_attn.k_proj",
    "language_model.model.layers.11.self_attn.o_proj",
    "language_model.model.layers.11.self_attn.q_proj",
    "language_model.model.layers.11.self_attn.v_proj",
    "language_model.model.layers.12.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.12.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.12.linear_attn.in_proj_a",
    "language_model.model.layers.12.linear_attn.in_proj_b",
    "language_model.model.layers.12.linear_attn.in_proj_qkv",
    "language_model.model.layers.12.linear_attn.in_proj_z",
    "language_model.model.layers.12.linear_attn.out_proj",
    "language_model.model.layers.12.mlp.shared_expert.down_proj",
    "language_model.model.layers.12.mlp.shared_expert.gate_proj",
    "language_model.model.layers.12.mlp.shared_expert.up_proj",
    "language_model.model.layers.12.mlp.shared_expert_gate",
    "language_model.model.layers.12.mlp.switch_mlp.down_proj",
    "language_model.model.layers.12.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.12.mlp.switch_mlp.up_proj",
    "language_model.model.layers.12.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.13.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.13.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.13.linear_attn.in_proj_a",
    "language_model.model.layers.13.linear_attn.in_proj_b",
    "language_model.model.layers.13.linear_attn.in_proj_qkv",
    "language_model.model.layers.13.linear_attn.in_proj_z",
    "language_model.model.layers.13.linear_attn.out_proj",
    "language_model.model.layers.13.mlp.shared_expert.down_proj",
    "language_model.model.layers.13.mlp.shared_expert.gate_proj",
    "language_model.model.layers.13.mlp.shared_expert.up_proj",
    "language_model.model.layers.13.mlp.shared_expert_gate",
    "language_model.model.layers.13.mlp.switch_mlp.down_proj",
    "language_model.model.layers.13.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.13.mlp.switch_mlp.up_proj",
    "language_model.model.layers.13.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.14.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.14.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.14.linear_attn.in_proj_a",
    "language_model.model.layers.14.linear_attn.in_proj_b",
    "language_model.model.layers.14.linear_attn.in_proj_qkv",
    "language_model.model.layers.14.linear_attn.in_proj_z",
    "language_model.model.layers.14.linear_attn.out_proj",
    "language_model.model.layers.14.mlp.shared_expert.down_proj",
    "language_model.model.layers.14.mlp.shared_expert.gate_proj",
    "language_model.model.layers.14.mlp.shared_expert.up_proj",
    "language_model.model.layers.14.mlp.shared_expert_gate",
    "language_model.model.layers.14.mlp.switch_mlp.down_proj",
    "language_model.model.layers.14.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.14.mlp.switch_mlp.up_proj",
    "language_model.model.layers.14.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.15.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.15.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.15.mlp.shared_expert.down_proj",
    "language_model.model.layers.15.mlp.shared_expert.gate_proj",
    "language_model.model.layers.15.mlp.shared_expert.up_proj",
    "language_model.model.layers.15.mlp.shared_expert_gate",
    "language_model.model.layers.15.mlp.switch_mlp.down_proj",
    "language_model.model.layers.15.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.15.mlp.switch_mlp.up_proj",
    "language_model.model.layers.15.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.15.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.15.self_attn.k_proj",
    "language_model.model.layers.15.self_attn.o_proj",
    "language_model.model.layers.15.self_attn.q_proj",
    "language_model.model.layers.15.self_attn.v_proj",
    "language_model.model.layers.16.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.16.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.16.linear_attn.in_proj_a",
    "language_model.model.layers.16.linear_attn.in_proj_b",
    "language_model.model.layers.16.linear_attn.in_proj_qkv",
    "language_model.model.layers.16.linear_attn.in_proj_z",
    "language_model.model.layers.16.linear_attn.out_proj",
    "language_model.model.layers.16.mlp.shared_expert.down_proj",
    "language_model.model.layers.16.mlp.shared_expert.gate_proj",
    "language_model.model.layers.16.mlp.shared_expert.up_proj",
    "language_model.model.layers.16.mlp.shared_expert_gate",
    "language_model.model.layers.16.mlp.switch_mlp.down_proj",
    "language_model.model.layers.16.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.16.mlp.switch_mlp.up_proj",
    "language_model.model.layers.16.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.17.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.17.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.17.linear_attn.in_proj_a",
    "language_model.model.layers.17.linear_attn.in_proj_b",
    "language_model.model.layers.17.linear_attn.in_proj_qkv",
    "language_model.model.layers.17.linear_attn.in_proj_z",
    "language_model.model.layers.17.linear_attn.out_proj",
    "language_model.model.layers.17.mlp.shared_expert.down_proj",
    "language_model.model.layers.17.mlp.shared_expert.gate_proj",
    "language_model.model.layers.17.mlp.shared_expert.up_proj",
    "language_model.model.layers.17.mlp.shared_expert_gate",
    "language_model.model.layers.17.mlp.switch_mlp.down_proj",
    "language_model.model.layers.17.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.17.mlp.switch_mlp.up_proj",
    "language_model.model.layers.17.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.18.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.18.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.18.linear_attn.in_proj_a",
    "language_model.model.layers.18.linear_attn.in_proj_b",
    "language_model.model.layers.18.linear_attn.in_proj_qkv",
    "language_model.model.layers.18.linear_attn.in_proj_z",
    "language_model.model.layers.18.linear_attn.out_proj",
    "language_model.model.layers.18.mlp.shared_expert.down_proj",
    "language_model.model.layers.18.mlp.shared_expert.gate_proj",
    "language_model.model.layers.18.mlp.shared_expert.up_proj",
    "language_model.model.layers.18.mlp.shared_expert_gate",
    "language_model.model.layers.18.mlp.switch_mlp.down_proj",
    "language_model.model.layers.18.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.18.mlp.switch_mlp.up_proj",
    "language_model.model.layers.18.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.19.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.19.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.19.mlp.shared_expert.down_proj",
    "language_model.model.layers.19.mlp.shared_expert.gate_proj",
    "language_model.model.layers.19.mlp.shared_expert.up_proj",
    "language_model.model.layers.19.mlp.shared_expert_gate",
    "language_model.model.layers.19.mlp.switch_mlp.down_proj",
    "language_model.model.layers.19.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.19.mlp.switch_mlp.up_proj",
    "language_model.model.layers.19.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.19.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.19.self_attn.k_proj",
    "language_model.model.layers.19.self_attn.o_proj",
    "language_model.model.layers.19.self_attn.q_proj",
    "language_model.model.layers.19.self_attn.v_proj",
    "language_model.model.layers.2.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.2.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.2.linear_attn.in_proj_a",
    "language_model.model.layers.2.linear_attn.in_proj_b",
    "language_model.model.layers.2.linear_attn.in_proj_qkv",
    "language_model.model.layers.2.linear_attn.in_proj_z",
    "language_model.model.layers.2.linear_attn.out_proj",
    "language_model.model.layers.2.mlp.shared_expert.down_proj",
    "language_model.model.layers.2.mlp.shared_expert.gate_proj",
    "language_model.model.layers.2.mlp.shared_expert.up_proj",
    "language_model.model.layers.2.mlp.shared_expert_gate",
    "language_model.model.layers.2.mlp.switch_mlp.down_proj",
    "language_model.model.layers.2.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.2.mlp.switch_mlp.up_proj",
    "language_model.model.layers.2.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.20.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.20.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.20.linear_attn.in_proj_a",
    "language_model.model.layers.20.linear_attn.in_proj_b",
    "language_model.model.layers.20.linear_attn.in_proj_qkv",
    "language_model.model.layers.20.linear_attn.in_proj_z",
    "language_model.model.layers.20.linear_attn.out_proj",
    "language_model.model.layers.20.mlp.shared_expert.down_proj",
    "language_model.model.layers.20.mlp.shared_expert.gate_proj",
    "language_model.model.layers.20.mlp.shared_expert.up_proj",
    "language_model.model.layers.20.mlp.shared_expert_gate",
    "language_model.model.layers.20.mlp.switch_mlp.down_proj",
    "language_model.model.layers.20.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.20.mlp.switch_mlp.up_proj",
    "language_model.model.layers.20.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.21.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.21.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.21.linear_attn.in_proj_a",
    "language_model.model.layers.21.linear_attn.in_proj_b",
    "language_model.model.layers.21.linear_attn.in_proj_qkv",
    "language_model.model.layers.21.linear_attn.in_proj_z",
    "language_model.model.layers.21.linear_attn.out_proj",
    "language_model.model.layers.21.mlp.shared_expert.down_proj",
    "language_model.model.layers.21.mlp.shared_expert.gate_proj",
    "language_model.model.layers.21.mlp.shared_expert.up_proj",
    "language_model.model.layers.21.mlp.shared_expert_gate",
    "language_model.model.layers.21.mlp.switch_mlp.down_proj",
    "language_model.model.layers.21.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.21.mlp.switch_mlp.up_proj",
    "language_model.model.layers.21.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.22.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.22.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.22.linear_attn.in_proj_a",
    "language_model.model.layers.22.linear_attn.in_proj_b",
    "language_model.model.layers.22.linear_attn.in_proj_qkv",
    "language_model.model.layers.22.linear_attn.in_proj_z",
    "language_model.model.layers.22.linear_attn.out_proj",
    "language_model.model.layers.22.mlp.shared_expert.down_proj",
    "language_model.model.layers.22.mlp.shared_expert.gate_proj",
    "language_model.model.layers.22.mlp.shared_expert.up_proj",
    "language_model.model.layers.22.mlp.shared_expert_gate",
    "language_model.model.layers.22.mlp.switch_mlp.down_proj",
    "language_model.model.layers.22.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.22.mlp.switch_mlp.up_proj",
    "language_model.model.layers.22.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.23.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.23.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.23.mlp.shared_expert.down_proj",
    "language_model.model.layers.23.mlp.shared_expert.gate_proj",
    "language_model.model.layers.23.mlp.shared_expert.up_proj",
    "language_model.model.layers.23.mlp.shared_expert_gate",
    "language_model.model.layers.23.mlp.switch_mlp.down_proj",
    "language_model.model.layers.23.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.23.mlp.switch_mlp.up_proj",
    "language_model.model.layers.23.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.23.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.23.self_attn.k_proj",
    "language_model.model.layers.23.self_attn.o_proj",
    "language_model.model.layers.23.self_attn.q_proj",
    "language_model.model.layers.23.self_attn.v_proj",
    "language_model.model.layers.24.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.24.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.24.linear_attn.in_proj_a",
    "language_model.model.layers.24.linear_attn.in_proj_b",
    "language_model.model.layers.24.linear_attn.in_proj_qkv",
    "language_model.model.layers.24.linear_attn.in_proj_z",
    "language_model.model.layers.24.linear_attn.out_proj",
    "language_model.model.layers.24.mlp.shared_expert.down_proj",
    "language_model.model.layers.24.mlp.shared_expert.gate_proj",
    "language_model.model.layers.24.mlp.shared_expert.up_proj",
    "language_model.model.layers.24.mlp.shared_expert_gate",
    "language_model.model.layers.24.mlp.switch_mlp.down_proj",
    "language_model.model.layers.24.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.24.mlp.switch_mlp.up_proj",
    "language_model.model.layers.24.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.25.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.25.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.25.linear_attn.in_proj_a",
    "language_model.model.layers.25.linear_attn.in_proj_b",
    "language_model.model.layers.25.linear_attn.in_proj_qkv",
    "language_model.model.layers.25.linear_attn.in_proj_z",
    "language_model.model.layers.25.linear_attn.out_proj",
    "language_model.model.layers.25.mlp.shared_expert.down_proj",
    "language_model.model.layers.25.mlp.shared_expert.gate_proj",
    "language_model.model.layers.25.mlp.shared_expert.up_proj",
    "language_model.model.layers.25.mlp.shared_expert_gate",
    "language_model.model.layers.25.mlp.switch_mlp.down_proj",
    "language_model.model.layers.25.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.25.mlp.switch_mlp.up_proj",
    "language_model.model.layers.25.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.26.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.26.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.26.linear_attn.in_proj_a",
    "language_model.model.layers.26.linear_attn.in_proj_b",
    "language_model.model.layers.26.linear_attn.in_proj_qkv",
    "language_model.model.layers.26.linear_attn.in_proj_z",
    "language_model.model.layers.26.linear_attn.out_proj",
    "language_model.model.layers.26.mlp.shared_expert.down_proj",
    "language_model.model.layers.26.mlp.shared_expert.gate_proj",
    "language_model.model.layers.26.mlp.shared_expert.up_proj",
    "language_model.model.layers.26.mlp.shared_expert_gate",
    "language_model.model.layers.26.mlp.switch_mlp.down_proj",
    "language_model.model.layers.26.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.26.mlp.switch_mlp.up_proj",
    "language_model.model.layers.26.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.27.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.27.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.27.mlp.shared_expert.down_proj",
    "language_model.model.layers.27.mlp.shared_expert.gate_proj",
    "language_model.model.layers.27.mlp.shared_expert.up_proj",
    "language_model.model.layers.27.mlp.shared_expert_gate",
    "language_model.model.layers.27.mlp.switch_mlp.down_proj",
    "language_model.model.layers.27.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.27.mlp.switch_mlp.up_proj",
    "language_model.model.layers.27.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.27.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.27.self_attn.k_proj",
    "language_model.model.layers.27.self_attn.o_proj",
    "language_model.model.layers.27.self_attn.q_proj",
    "language_model.model.layers.27.self_attn.v_proj",
    "language_model.model.layers.28.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.28.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.28.linear_attn.in_proj_a",
    "language_model.model.layers.28.linear_attn.in_proj_b",
    "language_model.model.layers.28.linear_attn.in_proj_qkv",
    "language_model.model.layers.28.linear_attn.in_proj_z",
    "language_model.model.layers.28.linear_attn.out_proj",
    "language_model.model.layers.28.mlp.shared_expert.down_proj",
    "language_model.model.layers.28.mlp.shared_expert.gate_proj",
    "language_model.model.layers.28.mlp.shared_expert.up_proj",
    "language_model.model.layers.28.mlp.shared_expert_gate",
    "language_model.model.layers.28.mlp.switch_mlp.down_proj",
    "language_model.model.layers.28.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.28.mlp.switch_mlp.up_proj",
    "language_model.model.layers.28.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.29.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.29.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.29.linear_attn.in_proj_a",
    "language_model.model.layers.29.linear_attn.in_proj_b",
    "language_model.model.layers.29.linear_attn.in_proj_qkv",
    "language_model.model.layers.29.linear_attn.in_proj_z",
    "language_model.model.layers.29.linear_attn.out_proj",
    "language_model.model.layers.29.mlp.shared_expert.down_proj",
    "language_model.model.layers.29.mlp.shared_expert.gate_proj",
    "language_model.model.layers.29.mlp.shared_expert.up_proj",
    "language_model.model.layers.29.mlp.shared_expert_gate",
    "language_model.model.layers.29.mlp.switch_mlp.down_proj",
    "language_model.model.layers.29.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.29.mlp.switch_mlp.up_proj",
    "language_model.model.layers.29.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.3.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.3.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.3.mlp.shared_expert.down_proj",
    "language_model.model.layers.3.mlp.shared_expert.gate_proj",
    "language_model.model.layers.3.mlp.shared_expert.up_proj",
    "language_model.model.layers.3.mlp.shared_expert_gate",
    "language_model.model.layers.3.mlp.switch_mlp.down_proj",
    "language_model.model.layers.3.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.3.mlp.switch_mlp.up_proj",
    "language_model.model.layers.3.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.3.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.3.self_attn.k_proj",
    "language_model.model.layers.3.self_attn.o_proj",
    "language_model.model.layers.3.self_attn.q_proj",
    "language_model.model.layers.3.self_attn.v_proj",
    "language_model.model.layers.30.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.30.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.30.linear_attn.in_proj_a",
    "language_model.model.layers.30.linear_attn.in_proj_b",
    "language_model.model.layers.30.linear_attn.in_proj_qkv",
    "language_model.model.layers.30.linear_attn.in_proj_z",
    "language_model.model.layers.30.linear_attn.out_proj",
    "language_model.model.layers.30.mlp.shared_expert.down_proj",
    "language_model.model.layers.30.mlp.shared_expert.gate_proj",
    "language_model.model.layers.30.mlp.shared_expert.up_proj",
    "language_model.model.layers.30.mlp.shared_expert_gate",
    "language_model.model.layers.30.mlp.switch_mlp.down_proj",
    "language_model.model.layers.30.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.30.mlp.switch_mlp.up_proj",
    "language_model.model.layers.30.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.31.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.31.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.31.mlp.shared_expert.down_proj",
    "language_model.model.layers.31.mlp.shared_expert.gate_proj",
    "language_model.model.layers.31.mlp.shared_expert.up_proj",
    "language_model.model.layers.31.mlp.shared_expert_gate",
    "language_model.model.layers.31.mlp.switch_mlp.down_proj",
    "language_model.model.layers.31.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.31.mlp.switch_mlp.up_proj",
    "language_model.model.layers.31.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.31.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.31.self_attn.k_proj",
    "language_model.model.layers.31.self_attn.o_proj",
    "language_model.model.layers.31.self_attn.q_proj",
    "language_model.model.layers.31.self_attn.v_proj",
    "language_model.model.layers.32.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.32.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.32.linear_attn.in_proj_a",
    "language_model.model.layers.32.linear_attn.in_proj_b",
    "language_model.model.layers.32.linear_attn.in_proj_qkv",
    "language_model.model.layers.32.linear_attn.in_proj_z",
    "language_model.model.layers.32.linear_attn.out_proj",
    "language_model.model.layers.32.mlp.shared_expert.down_proj",
    "language_model.model.layers.32.mlp.shared_expert.gate_proj",
    "language_model.model.layers.32.mlp.shared_expert.up_proj",
    "language_model.model.layers.32.mlp.shared_expert_gate",
    "language_model.model.layers.32.mlp.switch_mlp.down_proj",
    "language_model.model.layers.32.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.32.mlp.switch_mlp.up_proj",
    "language_model.model.layers.32.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.33.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.33.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.33.linear_attn.in_proj_a",
    "language_model.model.layers.33.linear_attn.in_proj_b",
    "language_model.model.layers.33.linear_attn.in_proj_qkv",
    "language_model.model.layers.33.linear_attn.in_proj_z",
    "language_model.model.layers.33.linear_attn.out_proj",
    "language_model.model.layers.33.mlp.shared_expert.down_proj",
    "language_model.model.layers.33.mlp.shared_expert.gate_proj",
    "language_model.model.layers.33.mlp.shared_expert.up_proj",
    "language_model.model.layers.33.mlp.shared_expert_gate",
    "language_model.model.layers.33.mlp.switch_mlp.down_proj",
    "language_model.model.layers.33.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.33.mlp.switch_mlp.up_proj",
    "language_model.model.layers.33.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.34.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.34.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.34.linear_attn.in_proj_a",
    "language_model.model.layers.34.linear_attn.in_proj_b",
    "language_model.model.layers.34.linear_attn.in_proj_qkv",
    "language_model.model.layers.34.linear_attn.in_proj_z",
    "language_model.model.layers.34.linear_attn.out_proj",
    "language_model.model.layers.34.mlp.shared_expert.down_proj",
    "language_model.model.layers.34.mlp.shared_expert.gate_proj",
    "language_model.model.layers.34.mlp.shared_expert.up_proj",
    "language_model.model.layers.34.mlp.shared_expert_gate",
    "language_model.model.layers.34.mlp.switch_mlp.down_proj",
    "language_model.model.layers.34.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.34.mlp.switch_mlp.up_proj",
    "language_model.model.layers.34.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.35.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.35.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.35.mlp.shared_expert.down_proj",
    "language_model.model.layers.35.mlp.shared_expert.gate_proj",
    "language_model.model.layers.35.mlp.shared_expert.up_proj",
    "language_model.model.layers.35.mlp.shared_expert_gate",
    "language_model.model.layers.35.mlp.switch_mlp.down_proj",
    "language_model.model.layers.35.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.35.mlp.switch_mlp.up_proj",
    "language_model.model.layers.35.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.35.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.35.self_attn.k_proj",
    "language_model.model.layers.35.self_attn.o_proj",
    "language_model.model.layers.35.self_attn.q_proj",
    "language_model.model.layers.35.self_attn.v_proj",
    "language_model.model.layers.36.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.36.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.36.linear_attn.in_proj_a",
    "language_model.model.layers.36.linear_attn.in_proj_b",
    "language_model.model.layers.36.linear_attn.in_proj_qkv",
    "language_model.model.layers.36.linear_attn.in_proj_z",
    "language_model.model.layers.36.linear_attn.out_proj",
    "language_model.model.layers.36.mlp.shared_expert.down_proj",
    "language_model.model.layers.36.mlp.shared_expert.gate_proj",
    "language_model.model.layers.36.mlp.shared_expert.up_proj",
    "language_model.model.layers.36.mlp.shared_expert_gate",
    "language_model.model.layers.36.mlp.switch_mlp.down_proj",
    "language_model.model.layers.36.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.36.mlp.switch_mlp.up_proj",
    "language_model.model.layers.36.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.37.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.37.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.37.linear_attn.in_proj_a",
    "language_model.model.layers.37.linear_attn.in_proj_b",
    "language_model.model.layers.37.linear_attn.in_proj_qkv",
    "language_model.model.layers.37.linear_attn.in_proj_z",
    "language_model.model.layers.37.linear_attn.out_proj",
    "language_model.model.layers.37.mlp.shared_expert.down_proj",
    "language_model.model.layers.37.mlp.shared_expert.gate_proj",
    "language_model.model.layers.37.mlp.shared_expert.up_proj",
    "language_model.model.layers.37.mlp.shared_expert_gate",
    "language_model.model.layers.37.mlp.switch_mlp.down_proj",
    "language_model.model.layers.37.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.37.mlp.switch_mlp.up_proj",
    "language_model.model.layers.37.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.38.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.38.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.38.linear_attn.in_proj_a",
    "language_model.model.layers.38.linear_attn.in_proj_b",
    "language_model.model.layers.38.linear_attn.in_proj_qkv",
    "language_model.model.layers.38.linear_attn.in_proj_z",
    "language_model.model.layers.38.linear_attn.out_proj",
    "language_model.model.layers.38.mlp.shared_expert.down_proj",
    "language_model.model.layers.38.mlp.shared_expert.gate_proj",
    "language_model.model.layers.38.mlp.shared_expert.up_proj",
    "language_model.model.layers.38.mlp.shared_expert_gate",
    "language_model.model.layers.38.mlp.switch_mlp.down_proj",
    "language_model.model.layers.38.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.38.mlp.switch_mlp.up_proj",
    "language_model.model.layers.38.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.39.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.39.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.39.mlp.shared_expert.down_proj",
    "language_model.model.layers.39.mlp.shared_expert.gate_proj",
    "language_model.model.layers.39.mlp.shared_expert.up_proj",
    "language_model.model.layers.39.mlp.shared_expert_gate",
    "language_model.model.layers.39.mlp.switch_mlp.down_proj",
    "language_model.model.layers.39.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.39.mlp.switch_mlp.up_proj",
    "language_model.model.layers.39.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.39.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.39.self_attn.k_proj",
    "language_model.model.layers.39.self_attn.o_proj",
    "language_model.model.layers.39.self_attn.q_proj",
    "language_model.model.layers.39.self_attn.v_proj",
    "language_model.model.layers.4.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.4.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.4.linear_attn.in_proj_a",
    "language_model.model.layers.4.linear_attn.in_proj_b",
    "language_model.model.layers.4.linear_attn.in_proj_qkv",
    "language_model.model.layers.4.linear_attn.in_proj_z",
    "language_model.model.layers.4.linear_attn.out_proj",
    "language_model.model.layers.4.mlp.shared_expert.down_proj",
    "language_model.model.layers.4.mlp.shared_expert.gate_proj",
    "language_model.model.layers.4.mlp.shared_expert.up_proj",
    "language_model.model.layers.4.mlp.shared_expert_gate",
    "language_model.model.layers.4.mlp.switch_mlp.down_proj",
    "language_model.model.layers.4.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.4.mlp.switch_mlp.up_proj",
    "language_model.model.layers.4.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.40.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.40.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.40.linear_attn.in_proj_a",
    "language_model.model.layers.40.linear_attn.in_proj_b",
    "language_model.model.layers.40.linear_attn.in_proj_qkv",
    "language_model.model.layers.40.linear_attn.in_proj_z",
    "language_model.model.layers.40.linear_attn.out_proj",
    "language_model.model.layers.40.mlp.shared_expert.down_proj",
    "language_model.model.layers.40.mlp.shared_expert.gate_proj",
    "language_model.model.layers.40.mlp.shared_expert.up_proj",
    "language_model.model.layers.40.mlp.shared_expert_gate",
    "language_model.model.layers.40.mlp.switch_mlp.down_proj",
    "language_model.model.layers.40.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.40.mlp.switch_mlp.up_proj",
    "language_model.model.layers.40.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.41.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.41.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.41.linear_attn.in_proj_a",
    "language_model.model.layers.41.linear_attn.in_proj_b",
    "language_model.model.layers.41.linear_attn.in_proj_qkv",
    "language_model.model.layers.41.linear_attn.in_proj_z",
    "language_model.model.layers.41.linear_attn.out_proj",
    "language_model.model.layers.41.mlp.shared_expert.down_proj",
    "language_model.model.layers.41.mlp.shared_expert.gate_proj",
    "language_model.model.layers.41.mlp.shared_expert.up_proj",
    "language_model.model.layers.41.mlp.shared_expert_gate",
    "language_model.model.layers.41.mlp.switch_mlp.down_proj",
    "language_model.model.layers.41.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.41.mlp.switch_mlp.up_proj",
    "language_model.model.layers.41.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.42.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.42.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.42.linear_attn.in_proj_a",
    "language_model.model.layers.42.linear_attn.in_proj_b",
    "language_model.model.layers.42.linear_attn.in_proj_qkv",
    "language_model.model.layers.42.linear_attn.in_proj_z",
    "language_model.model.layers.42.linear_attn.out_proj",
    "language_model.model.layers.42.mlp.shared_expert.down_proj",
    "language_model.model.layers.42.mlp.shared_expert.gate_proj",
    "language_model.model.layers.42.mlp.shared_expert.up_proj",
    "language_model.model.layers.42.mlp.shared_expert_gate",
    "language_model.model.layers.42.mlp.switch_mlp.down_proj",
    "language_model.model.layers.42.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.42.mlp.switch_mlp.up_proj",
    "language_model.model.layers.42.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.43.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.43.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.43.mlp.shared_expert.down_proj",
    "language_model.model.layers.43.mlp.shared_expert.gate_proj",
    "language_model.model.layers.43.mlp.shared_expert.up_proj",
    "language_model.model.layers.43.mlp.shared_expert_gate",
    "language_model.model.layers.43.mlp.switch_mlp.down_proj",
    "language_model.model.layers.43.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.43.mlp.switch_mlp.up_proj",
    "language_model.model.layers.43.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.43.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.43.self_attn.k_proj",
    "language_model.model.layers.43.self_attn.o_proj",
    "language_model.model.layers.43.self_attn.q_proj",
    "language_model.model.layers.43.self_attn.v_proj",
    "language_model.model.layers.44.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.44.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.44.linear_attn.in_proj_a",
    "language_model.model.layers.44.linear_attn.in_proj_b",
    "language_model.model.layers.44.linear_attn.in_proj_qkv",
    "language_model.model.layers.44.linear_attn.in_proj_z",
    "language_model.model.layers.44.linear_attn.out_proj",
    "language_model.model.layers.44.mlp.shared_expert.down_proj",
    "language_model.model.layers.44.mlp.shared_expert.gate_proj",
    "language_model.model.layers.44.mlp.shared_expert.up_proj",
    "language_model.model.layers.44.mlp.shared_expert_gate",
    "language_model.model.layers.44.mlp.switch_mlp.down_proj",
    "language_model.model.layers.44.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.44.mlp.switch_mlp.up_proj",
    "language_model.model.layers.44.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.45.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.45.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.45.linear_attn.in_proj_a",
    "language_model.model.layers.45.linear_attn.in_proj_b",
    "language_model.model.layers.45.linear_attn.in_proj_qkv",
    "language_model.model.layers.45.linear_attn.in_proj_z",
    "language_model.model.layers.45.linear_attn.out_proj",
    "language_model.model.layers.45.mlp.shared_expert.down_proj",
    "language_model.model.layers.45.mlp.shared_expert.gate_proj",
    "language_model.model.layers.45.mlp.shared_expert.up_proj",
    "language_model.model.layers.45.mlp.shared_expert_gate",
    "language_model.model.layers.45.mlp.switch_mlp.down_proj",
    "language_model.model.layers.45.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.45.mlp.switch_mlp.up_proj",
    "language_model.model.layers.45.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.46.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.46.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.46.linear_attn.in_proj_a",
    "language_model.model.layers.46.linear_attn.in_proj_b",
    "language_model.model.layers.46.linear_attn.in_proj_qkv",
    "language_model.model.layers.46.linear_attn.in_proj_z",
    "language_model.model.layers.46.linear_attn.out_proj",
    "language_model.model.layers.46.mlp.shared_expert.down_proj",
    "language_model.model.layers.46.mlp.shared_expert.gate_proj",
    "language_model.model.layers.46.mlp.shared_expert.up_proj",
    "language_model.model.layers.46.mlp.shared_expert_gate",
    "language_model.model.layers.46.mlp.switch_mlp.down_proj",
    "language_model.model.layers.46.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.46.mlp.switch_mlp.up_proj",
    "language_model.model.layers.46.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.47.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.47.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.47.mlp.shared_expert.down_proj",
    "language_model.model.layers.47.mlp.shared_expert.gate_proj",
    "language_model.model.layers.47.mlp.shared_expert.up_proj",
    "language_model.model.layers.47.mlp.shared_expert_gate",
    "language_model.model.layers.47.mlp.switch_mlp.down_proj",
    "language_model.model.layers.47.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.47.mlp.switch_mlp.up_proj",
    "language_model.model.layers.47.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.47.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.47.self_attn.k_proj",
    "language_model.model.layers.47.self_attn.o_proj",
    "language_model.model.layers.47.self_attn.q_proj",
    "language_model.model.layers.47.self_attn.v_proj",
    "language_model.model.layers.5.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.5.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.5.linear_attn.in_proj_a",
    "language_model.model.layers.5.linear_attn.in_proj_b",
    "language_model.model.layers.5.linear_attn.in_proj_qkv",
    "language_model.model.layers.5.linear_attn.in_proj_z",
    "language_model.model.layers.5.linear_attn.out_proj",
    "language_model.model.layers.5.mlp.shared_expert.down_proj",
    "language_model.model.layers.5.mlp.shared_expert.gate_proj",
    "language_model.model.layers.5.mlp.shared_expert.up_proj",
    "language_model.model.layers.5.mlp.shared_expert_gate",
    "language_model.model.layers.5.mlp.switch_mlp.down_proj",
    "language_model.model.layers.5.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.5.mlp.switch_mlp.up_proj",
    "language_model.model.layers.5.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.6.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.6.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.6.linear_attn.in_proj_a",
    "language_model.model.layers.6.linear_attn.in_proj_b",
    "language_model.model.layers.6.linear_attn.in_proj_qkv",
    "language_model.model.layers.6.linear_attn.in_proj_z",
    "language_model.model.layers.6.linear_attn.out_proj",
    "language_model.model.layers.6.mlp.shared_expert.down_proj",
    "language_model.model.layers.6.mlp.shared_expert.gate_proj",
    "language_model.model.layers.6.mlp.shared_expert.up_proj",
    "language_model.model.layers.6.mlp.shared_expert_gate",
    "language_model.model.layers.6.mlp.switch_mlp.down_proj",
    "language_model.model.layers.6.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.6.mlp.switch_mlp.up_proj",
    "language_model.model.layers.6.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.7.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.7.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.7.mlp.shared_expert.down_proj",
    "language_model.model.layers.7.mlp.shared_expert.gate_proj",
    "language_model.model.layers.7.mlp.shared_expert.up_proj",
    "language_model.model.layers.7.mlp.shared_expert_gate",
    "language_model.model.layers.7.mlp.switch_mlp.down_proj",
    "language_model.model.layers.7.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.7.mlp.switch_mlp.up_proj",
    "language_model.model.layers.7.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.7.self_attn.indexer.index_qk_proj",
    "language_model.model.layers.7.self_attn.k_proj",
    "language_model.model.layers.7.self_attn.o_proj",
    "language_model.model.layers.7.self_attn.q_proj",
    "language_model.model.layers.7.self_attn.v_proj",
    "language_model.model.layers.8.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.8.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.8.linear_attn.in_proj_a",
    "language_model.model.layers.8.linear_attn.in_proj_b",
    "language_model.model.layers.8.linear_attn.in_proj_qkv",
    "language_model.model.layers.8.linear_attn.in_proj_z",
    "language_model.model.layers.8.linear_attn.out_proj",
    "language_model.model.layers.8.mlp.shared_expert.down_proj",
    "language_model.model.layers.8.mlp.shared_expert.gate_proj",
    "language_model.model.layers.8.mlp.shared_expert.up_proj",
    "language_model.model.layers.8.mlp.shared_expert_gate",
    "language_model.model.layers.8.mlp.switch_mlp.down_proj",
    "language_model.model.layers.8.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.8.mlp.switch_mlp.up_proj",
    "language_model.model.layers.8.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.9.attn_hyper_connection.block_inject_weight",
    "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.9.attn_hyper_connection.input_mix_weight_up",
    "language_model.model.layers.9.linear_attn.in_proj_a",
    "language_model.model.layers.9.linear_attn.in_proj_b",
    "language_model.model.layers.9.linear_attn.in_proj_qkv",
    "language_model.model.layers.9.linear_attn.in_proj_z",
    "language_model.model.layers.9.linear_attn.out_proj",
    "language_model.model.layers.9.mlp.shared_expert.down_proj",
    "language_model.model.layers.9.mlp.shared_expert.gate_proj",
    "language_model.model.layers.9.mlp.shared_expert.up_proj",
    "language_model.model.layers.9.mlp.shared_expert_gate",
    "language_model.model.layers.9.mlp.switch_mlp.down_proj",
    "language_model.model.layers.9.mlp.switch_mlp.gate_proj",
    "language_model.model.layers.9.mlp.switch_mlp.up_proj",
    "language_model.model.layers.9.mlp_hyper_connection.block_inject_weight",
    "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down",
    "language_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up",
    "mtp.fc_embedding",
    "mtp.fc_hidden",
    "mtp.hyper_connection_mixer.input_mix_weight_down",
    "mtp.hyper_connection_mixer.input_mix_weight_up",
    "mtp.layers.0.attn_hyper_connection.block_inject_weight",
    "mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
    "mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
    "mtp.layers.0.mlp.shared_expert.down_proj",
    "mtp.layers.0.mlp.shared_expert.gate_proj",
    "mtp.layers.0.mlp.shared_expert.up_proj",
    "mtp.layers.0.mlp.shared_expert_gate",
    "mtp.layers.0.mlp.switch_mlp.down_proj",
    "mtp.layers.0.mlp.switch_mlp.gate_proj",
    "mtp.layers.0.mlp.switch_mlp.up_proj",
    "mtp.layers.0.mlp_hyper_connection.block_inject_weight",
    "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
    "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
    "mtp.layers.0.self_attn.indexer.index_qk_proj",
    "mtp.layers.0.self_attn.k_proj",
    "mtp.layers.0.self_attn.o_proj",
    "mtp.layers.0.self_attn.q_proj",
    "mtp.layers.0.self_attn.v_proj"
  ],
  "missing": [
    "language_model.lm_head",
    "language_model.model.hyper_connection_mixer.input_mix_weight_down",
    "language_model.model.hyper_connection_mixer.input_mix_weight_up"
  ],
  "mismatched": [],
  "zero_count_experts": 21
}