| { |
| "enabled": true, |
| "cache_path": "/Users/suhaarslan/.omlx/models/.oqe_imatrix/Qwen3-Coder-Next-fa8a2b98566a-s128-l512.npz", |
| "cache_reused": true, |
| "entry_count": 540, |
| "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": 16, |
| "micro_batches": 64, |
| "batch_plan": { |
| "micro_batch_size": 16, |
| "estimated_sample_bytes": 41943040, |
| "capture_budget_bytes": 805306368, |
| "system_available_bytes": 116156776448, |
| "metal_available_bytes": 115444240952, |
| "live_available_bytes": 115444240952, |
| "hidden_size": 2048, |
| "num_experts": 512, |
| "top_k": 10 |
| }, |
| "processed_samples": 1024, |
| "installed_modules": 541, |
| "capture_module_classes": { |
| "Linear": 48, |
| "QuantizedLinear": 349, |
| "QuantizedSwitchLinear": 144 |
| }, |
| "switch_capture_modules": 144, |
| "requires_expert_counts": true, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1950.050000000001, |
| "p10_count": 2588.0, |
| "median_count": 7577.0, |
| "max_count": 152578, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| }, |
| "rounds": [ |
| { |
| "processed_samples": 128, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 200.0, |
| "p10_count": 287.0, |
| "median_count": 925.0, |
| "max_count": 17777, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 256, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 449.0, |
| "p10_count": 606.0, |
| "median_count": 1853.0, |
| "max_count": 35200, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 384, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 697.3500000000004, |
| "p10_count": 934.0, |
| "median_count": 2828.0, |
| "max_count": 55355, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 512, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 931.3500000000004, |
| "p10_count": 1241.0, |
| "median_count": 3786.0, |
| "max_count": 74381, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 640, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1161.3500000000004, |
| "p10_count": 1553.0, |
| "median_count": 4701.0, |
| "max_count": 94052, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 768, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1444.3500000000004, |
| "p10_count": 1924.0, |
| "median_count": 5660.0, |
| "max_count": 111914, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 896, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1687.0, |
| "p10_count": 2238.0, |
| "median_count": 6589.5, |
| "max_count": 131890, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| }, |
| { |
| "processed_samples": 1024, |
| "coverage_sufficient": false, |
| "collection_sufficient": false, |
| "coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1950.050000000001, |
| "p10_count": 2588.0, |
| "median_count": 7577.0, |
| "max_count": 152578, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| } |
| ] |
| }, |
| "expert_coverage": { |
| "has_expert_counts": true, |
| "expert_modules": 144, |
| "total_experts": 73728, |
| "active_experts": 73725, |
| "zero_count_experts": 3, |
| "active_ratio": 0.9999593098958334, |
| "min_count": 0, |
| "p05_count": 1950.050000000001, |
| "p10_count": 2588.0, |
| "median_count": 7577.0, |
| "max_count": 152578, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| }, |
| "applied": [ |
| "model.layers.0.linear_attn.in_proj_ba", |
| "model.layers.0.linear_attn.in_proj_qkvz", |
| "model.layers.0.linear_attn.out_proj", |
| "model.layers.0.mlp.shared_expert.down_proj", |
| "model.layers.0.mlp.shared_expert.gate_proj", |
| "model.layers.0.mlp.shared_expert.up_proj", |
| "model.layers.0.mlp.shared_expert_gate", |
| "model.layers.0.mlp.switch_mlp.down_proj", |
| "model.layers.0.mlp.switch_mlp.gate_proj", |
| "model.layers.0.mlp.switch_mlp.up_proj", |
| "model.layers.1.linear_attn.in_proj_ba", |
| "model.layers.1.linear_attn.in_proj_qkvz", |
| "model.layers.1.linear_attn.out_proj", |
| "model.layers.1.mlp.shared_expert.down_proj", |
| "model.layers.1.mlp.shared_expert.gate_proj", |
| "model.layers.1.mlp.shared_expert.up_proj", |
| "model.layers.1.mlp.shared_expert_gate", |
| "model.layers.1.mlp.switch_mlp.down_proj", |
| "model.layers.1.mlp.switch_mlp.gate_proj", |
| "model.layers.1.mlp.switch_mlp.up_proj", |
| "model.layers.10.linear_attn.in_proj_ba", |
| "model.layers.10.linear_attn.in_proj_qkvz", |
| "model.layers.10.linear_attn.out_proj", |
| "model.layers.10.mlp.shared_expert.down_proj", |
| "model.layers.10.mlp.shared_expert.gate_proj", |
| "model.layers.10.mlp.shared_expert.up_proj", |
| "model.layers.10.mlp.shared_expert_gate", |
| "model.layers.10.mlp.switch_mlp.down_proj", |
| "model.layers.10.mlp.switch_mlp.gate_proj", |
| "model.layers.10.mlp.switch_mlp.up_proj", |
| "model.layers.11.mlp.shared_expert.down_proj", |
| "model.layers.11.mlp.shared_expert.gate_proj", |
| "model.layers.11.mlp.shared_expert.up_proj", |
| "model.layers.11.mlp.shared_expert_gate", |
| "model.layers.11.mlp.switch_mlp.down_proj", |
| "model.layers.11.mlp.switch_mlp.gate_proj", |
| "model.layers.11.mlp.switch_mlp.up_proj", |
| "model.layers.11.self_attn.k_proj", |
| "model.layers.11.self_attn.o_proj", |
| "model.layers.11.self_attn.q_proj", |
| "model.layers.11.self_attn.v_proj", |
| "model.layers.12.linear_attn.in_proj_ba", |
| "model.layers.12.linear_attn.in_proj_qkvz", |
| "model.layers.12.linear_attn.out_proj", |
| "model.layers.12.mlp.shared_expert.down_proj", |
| "model.layers.12.mlp.shared_expert.gate_proj", |
| "model.layers.12.mlp.shared_expert.up_proj", |
| "model.layers.12.mlp.shared_expert_gate", |
| "model.layers.12.mlp.switch_mlp.down_proj", |
| "model.layers.12.mlp.switch_mlp.gate_proj", |
| "model.layers.12.mlp.switch_mlp.up_proj", |
| "model.layers.13.linear_attn.in_proj_ba", |
| "model.layers.13.linear_attn.in_proj_qkvz", |
| "model.layers.13.linear_attn.out_proj", |
| "model.layers.13.mlp.shared_expert.down_proj", |
| "model.layers.13.mlp.shared_expert.gate_proj", |
| "model.layers.13.mlp.shared_expert.up_proj", |
| "model.layers.13.mlp.shared_expert_gate", |
| "model.layers.13.mlp.switch_mlp.down_proj", |
| "model.layers.13.mlp.switch_mlp.gate_proj", |
| "model.layers.13.mlp.switch_mlp.up_proj", |
| "model.layers.14.linear_attn.in_proj_ba", |
| "model.layers.14.linear_attn.in_proj_qkvz", |
| "model.layers.14.linear_attn.out_proj", |
| "model.layers.14.mlp.shared_expert.down_proj", |
| "model.layers.14.mlp.shared_expert.gate_proj", |
| "model.layers.14.mlp.shared_expert.up_proj", |
| "model.layers.14.mlp.shared_expert_gate", |
| "model.layers.14.mlp.switch_mlp.down_proj", |
| "model.layers.14.mlp.switch_mlp.gate_proj", |
| "model.layers.14.mlp.switch_mlp.up_proj", |
| "model.layers.15.mlp.shared_expert.down_proj", |
| "model.layers.15.mlp.shared_expert.gate_proj", |
| "model.layers.15.mlp.shared_expert.up_proj", |
| "model.layers.15.mlp.shared_expert_gate", |
| "model.layers.15.mlp.switch_mlp.down_proj", |
| "model.layers.15.mlp.switch_mlp.gate_proj", |
| "model.layers.15.mlp.switch_mlp.up_proj", |
| "model.layers.15.self_attn.k_proj", |
| "model.layers.15.self_attn.o_proj", |
| "model.layers.15.self_attn.q_proj", |
| "model.layers.15.self_attn.v_proj", |
| "model.layers.16.linear_attn.in_proj_ba", |
| "model.layers.16.linear_attn.in_proj_qkvz", |
| "model.layers.16.linear_attn.out_proj", |
| "model.layers.16.mlp.shared_expert.down_proj", |
| "model.layers.16.mlp.shared_expert.gate_proj", |
| "model.layers.16.mlp.shared_expert.up_proj", |
| "model.layers.16.mlp.shared_expert_gate", |
| "model.layers.16.mlp.switch_mlp.down_proj", |
| "model.layers.16.mlp.switch_mlp.gate_proj", |
| "model.layers.16.mlp.switch_mlp.up_proj", |
| "model.layers.17.linear_attn.in_proj_ba", |
| "model.layers.17.linear_attn.in_proj_qkvz", |
| "model.layers.17.linear_attn.out_proj", |
| "model.layers.17.mlp.shared_expert.down_proj", |
| "model.layers.17.mlp.shared_expert.gate_proj", |
| "model.layers.17.mlp.shared_expert.up_proj", |
| "model.layers.17.mlp.shared_expert_gate", |
| "model.layers.17.mlp.switch_mlp.down_proj", |
| "model.layers.17.mlp.switch_mlp.gate_proj", |
| "model.layers.17.mlp.switch_mlp.up_proj", |
| "model.layers.18.linear_attn.in_proj_ba", |
| "model.layers.18.linear_attn.in_proj_qkvz", |
| "model.layers.18.linear_attn.out_proj", |
| "model.layers.18.mlp.shared_expert.down_proj", |
| "model.layers.18.mlp.shared_expert.gate_proj", |
| "model.layers.18.mlp.shared_expert.up_proj", |
| "model.layers.18.mlp.shared_expert_gate", |
| "model.layers.18.mlp.switch_mlp.down_proj", |
| "model.layers.18.mlp.switch_mlp.gate_proj", |
| "model.layers.18.mlp.switch_mlp.up_proj", |
| "model.layers.19.mlp.shared_expert.down_proj", |
| "model.layers.19.mlp.shared_expert.gate_proj", |
| "model.layers.19.mlp.shared_expert.up_proj", |
| "model.layers.19.mlp.shared_expert_gate", |
| "model.layers.19.mlp.switch_mlp.down_proj", |
| "model.layers.19.mlp.switch_mlp.gate_proj", |
| "model.layers.19.mlp.switch_mlp.up_proj", |
| "model.layers.19.self_attn.k_proj", |
| "model.layers.19.self_attn.o_proj", |
| "model.layers.19.self_attn.q_proj", |
| "model.layers.19.self_attn.v_proj", |
| "model.layers.2.linear_attn.in_proj_ba", |
| "model.layers.2.linear_attn.in_proj_qkvz", |
| "model.layers.2.linear_attn.out_proj", |
| "model.layers.2.mlp.shared_expert.down_proj", |
| "model.layers.2.mlp.shared_expert.gate_proj", |
| "model.layers.2.mlp.shared_expert.up_proj", |
| "model.layers.2.mlp.shared_expert_gate", |
| "model.layers.2.mlp.switch_mlp.down_proj", |
| "model.layers.2.mlp.switch_mlp.gate_proj", |
| "model.layers.2.mlp.switch_mlp.up_proj", |
| "model.layers.20.linear_attn.in_proj_ba", |
| "model.layers.20.linear_attn.in_proj_qkvz", |
| "model.layers.20.linear_attn.out_proj", |
| "model.layers.20.mlp.shared_expert.down_proj", |
| "model.layers.20.mlp.shared_expert.gate_proj", |
| "model.layers.20.mlp.shared_expert.up_proj", |
| "model.layers.20.mlp.shared_expert_gate", |
| "model.layers.20.mlp.switch_mlp.down_proj", |
| "model.layers.20.mlp.switch_mlp.gate_proj", |
| "model.layers.20.mlp.switch_mlp.up_proj", |
| "model.layers.21.linear_attn.in_proj_ba", |
| "model.layers.21.linear_attn.in_proj_qkvz", |
| "model.layers.21.linear_attn.out_proj", |
| "model.layers.21.mlp.shared_expert.down_proj", |
| "model.layers.21.mlp.shared_expert.gate_proj", |
| "model.layers.21.mlp.shared_expert.up_proj", |
| "model.layers.21.mlp.shared_expert_gate", |
| "model.layers.21.mlp.switch_mlp.down_proj", |
| "model.layers.21.mlp.switch_mlp.gate_proj", |
| "model.layers.21.mlp.switch_mlp.up_proj", |
| "model.layers.22.linear_attn.in_proj_ba", |
| "model.layers.22.linear_attn.in_proj_qkvz", |
| "model.layers.22.linear_attn.out_proj", |
| "model.layers.22.mlp.shared_expert.down_proj", |
| "model.layers.22.mlp.shared_expert.gate_proj", |
| "model.layers.22.mlp.shared_expert.up_proj", |
| "model.layers.22.mlp.shared_expert_gate", |
| "model.layers.22.mlp.switch_mlp.down_proj", |
| "model.layers.22.mlp.switch_mlp.gate_proj", |
| "model.layers.22.mlp.switch_mlp.up_proj", |
| "model.layers.23.mlp.shared_expert.down_proj", |
| "model.layers.23.mlp.shared_expert.gate_proj", |
| "model.layers.23.mlp.shared_expert.up_proj", |
| "model.layers.23.mlp.shared_expert_gate", |
| "model.layers.23.mlp.switch_mlp.down_proj", |
| "model.layers.23.mlp.switch_mlp.gate_proj", |
| "model.layers.23.mlp.switch_mlp.up_proj", |
| "model.layers.23.self_attn.k_proj", |
| "model.layers.23.self_attn.o_proj", |
| "model.layers.23.self_attn.q_proj", |
| "model.layers.23.self_attn.v_proj", |
| "model.layers.24.linear_attn.in_proj_ba", |
| "model.layers.24.linear_attn.in_proj_qkvz", |
| "model.layers.24.linear_attn.out_proj", |
| "model.layers.24.mlp.shared_expert.down_proj", |
| "model.layers.24.mlp.shared_expert.gate_proj", |
| "model.layers.24.mlp.shared_expert.up_proj", |
| "model.layers.24.mlp.shared_expert_gate", |
| "model.layers.24.mlp.switch_mlp.down_proj", |
| "model.layers.24.mlp.switch_mlp.gate_proj", |
| "model.layers.24.mlp.switch_mlp.up_proj", |
| "model.layers.25.linear_attn.in_proj_ba", |
| "model.layers.25.linear_attn.in_proj_qkvz", |
| "model.layers.25.linear_attn.out_proj", |
| "model.layers.25.mlp.shared_expert.down_proj", |
| "model.layers.25.mlp.shared_expert.gate_proj", |
| "model.layers.25.mlp.shared_expert.up_proj", |
| "model.layers.25.mlp.shared_expert_gate", |
| "model.layers.25.mlp.switch_mlp.down_proj", |
| "model.layers.25.mlp.switch_mlp.gate_proj", |
| "model.layers.25.mlp.switch_mlp.up_proj", |
| "model.layers.26.linear_attn.in_proj_ba", |
| "model.layers.26.linear_attn.in_proj_qkvz", |
| "model.layers.26.linear_attn.out_proj", |
| "model.layers.26.mlp.shared_expert.down_proj", |
| "model.layers.26.mlp.shared_expert.gate_proj", |
| "model.layers.26.mlp.shared_expert.up_proj", |
| "model.layers.26.mlp.shared_expert_gate", |
| "model.layers.26.mlp.switch_mlp.down_proj", |
| "model.layers.26.mlp.switch_mlp.gate_proj", |
| "model.layers.26.mlp.switch_mlp.up_proj", |
| "model.layers.27.mlp.shared_expert.down_proj", |
| "model.layers.27.mlp.shared_expert.gate_proj", |
| "model.layers.27.mlp.shared_expert.up_proj", |
| "model.layers.27.mlp.shared_expert_gate", |
| "model.layers.27.mlp.switch_mlp.down_proj", |
| "model.layers.27.mlp.switch_mlp.gate_proj", |
| "model.layers.27.mlp.switch_mlp.up_proj", |
| "model.layers.27.self_attn.k_proj", |
| "model.layers.27.self_attn.o_proj", |
| "model.layers.27.self_attn.q_proj", |
| "model.layers.27.self_attn.v_proj", |
| "model.layers.28.linear_attn.in_proj_ba", |
| "model.layers.28.linear_attn.in_proj_qkvz", |
| "model.layers.28.linear_attn.out_proj", |
| "model.layers.28.mlp.shared_expert.down_proj", |
| "model.layers.28.mlp.shared_expert.gate_proj", |
| "model.layers.28.mlp.shared_expert.up_proj", |
| "model.layers.28.mlp.shared_expert_gate", |
| "model.layers.28.mlp.switch_mlp.down_proj", |
| "model.layers.28.mlp.switch_mlp.gate_proj", |
| "model.layers.28.mlp.switch_mlp.up_proj", |
| "model.layers.29.linear_attn.in_proj_ba", |
| "model.layers.29.linear_attn.in_proj_qkvz", |
| "model.layers.29.linear_attn.out_proj", |
| "model.layers.29.mlp.shared_expert.down_proj", |
| "model.layers.29.mlp.shared_expert.gate_proj", |
| "model.layers.29.mlp.shared_expert.up_proj", |
| "model.layers.29.mlp.shared_expert_gate", |
| "model.layers.29.mlp.switch_mlp.down_proj", |
| "model.layers.29.mlp.switch_mlp.gate_proj", |
| "model.layers.29.mlp.switch_mlp.up_proj", |
| "model.layers.3.mlp.shared_expert.down_proj", |
| "model.layers.3.mlp.shared_expert.gate_proj", |
| "model.layers.3.mlp.shared_expert.up_proj", |
| "model.layers.3.mlp.shared_expert_gate", |
| "model.layers.3.mlp.switch_mlp.down_proj", |
| "model.layers.3.mlp.switch_mlp.gate_proj", |
| "model.layers.3.mlp.switch_mlp.up_proj", |
| "model.layers.3.self_attn.k_proj", |
| "model.layers.3.self_attn.o_proj", |
| "model.layers.3.self_attn.q_proj", |
| "model.layers.3.self_attn.v_proj", |
| "model.layers.30.linear_attn.in_proj_ba", |
| "model.layers.30.linear_attn.in_proj_qkvz", |
| "model.layers.30.linear_attn.out_proj", |
| "model.layers.30.mlp.shared_expert.down_proj", |
| "model.layers.30.mlp.shared_expert.gate_proj", |
| "model.layers.30.mlp.shared_expert.up_proj", |
| "model.layers.30.mlp.shared_expert_gate", |
| "model.layers.30.mlp.switch_mlp.down_proj", |
| "model.layers.30.mlp.switch_mlp.gate_proj", |
| "model.layers.30.mlp.switch_mlp.up_proj", |
| "model.layers.31.mlp.shared_expert.down_proj", |
| "model.layers.31.mlp.shared_expert.gate_proj", |
| "model.layers.31.mlp.shared_expert.up_proj", |
| "model.layers.31.mlp.shared_expert_gate", |
| "model.layers.31.mlp.switch_mlp.down_proj", |
| "model.layers.31.mlp.switch_mlp.gate_proj", |
| "model.layers.31.mlp.switch_mlp.up_proj", |
| "model.layers.31.self_attn.k_proj", |
| "model.layers.31.self_attn.o_proj", |
| "model.layers.31.self_attn.q_proj", |
| "model.layers.31.self_attn.v_proj", |
| "model.layers.32.linear_attn.in_proj_ba", |
| "model.layers.32.linear_attn.in_proj_qkvz", |
| "model.layers.32.linear_attn.out_proj", |
| "model.layers.32.mlp.shared_expert.down_proj", |
| "model.layers.32.mlp.shared_expert.gate_proj", |
| "model.layers.32.mlp.shared_expert.up_proj", |
| "model.layers.32.mlp.shared_expert_gate", |
| "model.layers.32.mlp.switch_mlp.down_proj", |
| "model.layers.32.mlp.switch_mlp.gate_proj", |
| "model.layers.32.mlp.switch_mlp.up_proj", |
| "model.layers.33.linear_attn.in_proj_ba", |
| "model.layers.33.linear_attn.in_proj_qkvz", |
| "model.layers.33.linear_attn.out_proj", |
| "model.layers.33.mlp.shared_expert.down_proj", |
| "model.layers.33.mlp.shared_expert.gate_proj", |
| "model.layers.33.mlp.shared_expert.up_proj", |
| "model.layers.33.mlp.shared_expert_gate", |
| "model.layers.33.mlp.switch_mlp.down_proj", |
| "model.layers.33.mlp.switch_mlp.gate_proj", |
| "model.layers.33.mlp.switch_mlp.up_proj", |
| "model.layers.34.linear_attn.in_proj_ba", |
| "model.layers.34.linear_attn.in_proj_qkvz", |
| "model.layers.34.linear_attn.out_proj", |
| "model.layers.34.mlp.shared_expert.down_proj", |
| "model.layers.34.mlp.shared_expert.gate_proj", |
| "model.layers.34.mlp.shared_expert.up_proj", |
| "model.layers.34.mlp.shared_expert_gate", |
| "model.layers.34.mlp.switch_mlp.down_proj", |
| "model.layers.34.mlp.switch_mlp.gate_proj", |
| "model.layers.34.mlp.switch_mlp.up_proj", |
| "model.layers.35.mlp.shared_expert.down_proj", |
| "model.layers.35.mlp.shared_expert.gate_proj", |
| "model.layers.35.mlp.shared_expert.up_proj", |
| "model.layers.35.mlp.shared_expert_gate", |
| "model.layers.35.mlp.switch_mlp.down_proj", |
| "model.layers.35.mlp.switch_mlp.gate_proj", |
| "model.layers.35.mlp.switch_mlp.up_proj", |
| "model.layers.35.self_attn.k_proj", |
| "model.layers.35.self_attn.o_proj", |
| "model.layers.35.self_attn.q_proj", |
| "model.layers.35.self_attn.v_proj", |
| "model.layers.36.linear_attn.in_proj_ba", |
| "model.layers.36.linear_attn.in_proj_qkvz", |
| "model.layers.36.linear_attn.out_proj", |
| "model.layers.36.mlp.shared_expert.down_proj", |
| "model.layers.36.mlp.shared_expert.gate_proj", |
| "model.layers.36.mlp.shared_expert.up_proj", |
| "model.layers.36.mlp.shared_expert_gate", |
| "model.layers.36.mlp.switch_mlp.down_proj", |
| "model.layers.36.mlp.switch_mlp.gate_proj", |
| "model.layers.36.mlp.switch_mlp.up_proj", |
| "model.layers.37.linear_attn.in_proj_ba", |
| "model.layers.37.linear_attn.in_proj_qkvz", |
| "model.layers.37.linear_attn.out_proj", |
| "model.layers.37.mlp.shared_expert.down_proj", |
| "model.layers.37.mlp.shared_expert.gate_proj", |
| "model.layers.37.mlp.shared_expert.up_proj", |
| "model.layers.37.mlp.shared_expert_gate", |
| "model.layers.37.mlp.switch_mlp.down_proj", |
| "model.layers.37.mlp.switch_mlp.gate_proj", |
| "model.layers.37.mlp.switch_mlp.up_proj", |
| "model.layers.38.linear_attn.in_proj_ba", |
| "model.layers.38.linear_attn.in_proj_qkvz", |
| "model.layers.38.linear_attn.out_proj", |
| "model.layers.38.mlp.shared_expert.down_proj", |
| "model.layers.38.mlp.shared_expert.gate_proj", |
| "model.layers.38.mlp.shared_expert.up_proj", |
| "model.layers.38.mlp.shared_expert_gate", |
| "model.layers.38.mlp.switch_mlp.down_proj", |
| "model.layers.38.mlp.switch_mlp.gate_proj", |
| "model.layers.38.mlp.switch_mlp.up_proj", |
| "model.layers.39.mlp.shared_expert.down_proj", |
| "model.layers.39.mlp.shared_expert.gate_proj", |
| "model.layers.39.mlp.shared_expert.up_proj", |
| "model.layers.39.mlp.shared_expert_gate", |
| "model.layers.39.mlp.switch_mlp.down_proj", |
| "model.layers.39.mlp.switch_mlp.gate_proj", |
| "model.layers.39.mlp.switch_mlp.up_proj", |
| "model.layers.39.self_attn.k_proj", |
| "model.layers.39.self_attn.o_proj", |
| "model.layers.39.self_attn.q_proj", |
| "model.layers.39.self_attn.v_proj", |
| "model.layers.4.linear_attn.in_proj_ba", |
| "model.layers.4.linear_attn.in_proj_qkvz", |
| "model.layers.4.linear_attn.out_proj", |
| "model.layers.4.mlp.shared_expert.down_proj", |
| "model.layers.4.mlp.shared_expert.gate_proj", |
| "model.layers.4.mlp.shared_expert.up_proj", |
| "model.layers.4.mlp.shared_expert_gate", |
| "model.layers.4.mlp.switch_mlp.down_proj", |
| "model.layers.4.mlp.switch_mlp.gate_proj", |
| "model.layers.4.mlp.switch_mlp.up_proj", |
| "model.layers.40.linear_attn.in_proj_ba", |
| "model.layers.40.linear_attn.in_proj_qkvz", |
| "model.layers.40.linear_attn.out_proj", |
| "model.layers.40.mlp.shared_expert.down_proj", |
| "model.layers.40.mlp.shared_expert.gate_proj", |
| "model.layers.40.mlp.shared_expert.up_proj", |
| "model.layers.40.mlp.shared_expert_gate", |
| "model.layers.40.mlp.switch_mlp.down_proj", |
| "model.layers.40.mlp.switch_mlp.gate_proj", |
| "model.layers.40.mlp.switch_mlp.up_proj", |
| "model.layers.41.linear_attn.in_proj_ba", |
| "model.layers.41.linear_attn.in_proj_qkvz", |
| "model.layers.41.linear_attn.out_proj", |
| "model.layers.41.mlp.shared_expert.down_proj", |
| "model.layers.41.mlp.shared_expert.gate_proj", |
| "model.layers.41.mlp.shared_expert.up_proj", |
| "model.layers.41.mlp.shared_expert_gate", |
| "model.layers.41.mlp.switch_mlp.down_proj", |
| "model.layers.41.mlp.switch_mlp.gate_proj", |
| "model.layers.41.mlp.switch_mlp.up_proj", |
| "model.layers.42.linear_attn.in_proj_ba", |
| "model.layers.42.linear_attn.in_proj_qkvz", |
| "model.layers.42.linear_attn.out_proj", |
| "model.layers.42.mlp.shared_expert.down_proj", |
| "model.layers.42.mlp.shared_expert.gate_proj", |
| "model.layers.42.mlp.shared_expert.up_proj", |
| "model.layers.42.mlp.shared_expert_gate", |
| "model.layers.42.mlp.switch_mlp.down_proj", |
| "model.layers.42.mlp.switch_mlp.gate_proj", |
| "model.layers.42.mlp.switch_mlp.up_proj", |
| "model.layers.43.mlp.shared_expert.down_proj", |
| "model.layers.43.mlp.shared_expert.gate_proj", |
| "model.layers.43.mlp.shared_expert.up_proj", |
| "model.layers.43.mlp.shared_expert_gate", |
| "model.layers.43.mlp.switch_mlp.down_proj", |
| "model.layers.43.mlp.switch_mlp.gate_proj", |
| "model.layers.43.mlp.switch_mlp.up_proj", |
| "model.layers.43.self_attn.k_proj", |
| "model.layers.43.self_attn.o_proj", |
| "model.layers.43.self_attn.q_proj", |
| "model.layers.43.self_attn.v_proj", |
| "model.layers.44.linear_attn.in_proj_ba", |
| "model.layers.44.linear_attn.in_proj_qkvz", |
| "model.layers.44.linear_attn.out_proj", |
| "model.layers.44.mlp.shared_expert.down_proj", |
| "model.layers.44.mlp.shared_expert.gate_proj", |
| "model.layers.44.mlp.shared_expert.up_proj", |
| "model.layers.44.mlp.shared_expert_gate", |
| "model.layers.44.mlp.switch_mlp.down_proj", |
| "model.layers.44.mlp.switch_mlp.gate_proj", |
| "model.layers.44.mlp.switch_mlp.up_proj", |
| "model.layers.45.linear_attn.in_proj_ba", |
| "model.layers.45.linear_attn.in_proj_qkvz", |
| "model.layers.45.linear_attn.out_proj", |
| "model.layers.45.mlp.shared_expert.down_proj", |
| "model.layers.45.mlp.shared_expert.gate_proj", |
| "model.layers.45.mlp.shared_expert.up_proj", |
| "model.layers.45.mlp.shared_expert_gate", |
| "model.layers.45.mlp.switch_mlp.down_proj", |
| "model.layers.45.mlp.switch_mlp.gate_proj", |
| "model.layers.45.mlp.switch_mlp.up_proj", |
| "model.layers.46.linear_attn.in_proj_ba", |
| "model.layers.46.linear_attn.in_proj_qkvz", |
| "model.layers.46.linear_attn.out_proj", |
| "model.layers.46.mlp.shared_expert.down_proj", |
| "model.layers.46.mlp.shared_expert.gate_proj", |
| "model.layers.46.mlp.shared_expert.up_proj", |
| "model.layers.46.mlp.shared_expert_gate", |
| "model.layers.46.mlp.switch_mlp.down_proj", |
| "model.layers.46.mlp.switch_mlp.gate_proj", |
| "model.layers.46.mlp.switch_mlp.up_proj", |
| "model.layers.47.mlp.shared_expert.down_proj", |
| "model.layers.47.mlp.shared_expert.gate_proj", |
| "model.layers.47.mlp.shared_expert.up_proj", |
| "model.layers.47.mlp.shared_expert_gate", |
| "model.layers.47.mlp.switch_mlp.down_proj", |
| "model.layers.47.mlp.switch_mlp.gate_proj", |
| "model.layers.47.mlp.switch_mlp.up_proj", |
| "model.layers.47.self_attn.k_proj", |
| "model.layers.47.self_attn.o_proj", |
| "model.layers.47.self_attn.q_proj", |
| "model.layers.47.self_attn.v_proj", |
| "model.layers.5.linear_attn.in_proj_ba", |
| "model.layers.5.linear_attn.in_proj_qkvz", |
| "model.layers.5.linear_attn.out_proj", |
| "model.layers.5.mlp.shared_expert.down_proj", |
| "model.layers.5.mlp.shared_expert.gate_proj", |
| "model.layers.5.mlp.shared_expert.up_proj", |
| "model.layers.5.mlp.shared_expert_gate", |
| "model.layers.5.mlp.switch_mlp.down_proj", |
| "model.layers.5.mlp.switch_mlp.gate_proj", |
| "model.layers.5.mlp.switch_mlp.up_proj", |
| "model.layers.6.linear_attn.in_proj_ba", |
| "model.layers.6.linear_attn.in_proj_qkvz", |
| "model.layers.6.linear_attn.out_proj", |
| "model.layers.6.mlp.shared_expert.down_proj", |
| "model.layers.6.mlp.shared_expert.gate_proj", |
| "model.layers.6.mlp.shared_expert.up_proj", |
| "model.layers.6.mlp.shared_expert_gate", |
| "model.layers.6.mlp.switch_mlp.down_proj", |
| "model.layers.6.mlp.switch_mlp.gate_proj", |
| "model.layers.6.mlp.switch_mlp.up_proj", |
| "model.layers.7.mlp.shared_expert.down_proj", |
| "model.layers.7.mlp.shared_expert.gate_proj", |
| "model.layers.7.mlp.shared_expert.up_proj", |
| "model.layers.7.mlp.shared_expert_gate", |
| "model.layers.7.mlp.switch_mlp.down_proj", |
| "model.layers.7.mlp.switch_mlp.gate_proj", |
| "model.layers.7.mlp.switch_mlp.up_proj", |
| "model.layers.7.self_attn.k_proj", |
| "model.layers.7.self_attn.o_proj", |
| "model.layers.7.self_attn.q_proj", |
| "model.layers.7.self_attn.v_proj", |
| "model.layers.8.linear_attn.in_proj_ba", |
| "model.layers.8.linear_attn.in_proj_qkvz", |
| "model.layers.8.linear_attn.out_proj", |
| "model.layers.8.mlp.shared_expert.down_proj", |
| "model.layers.8.mlp.shared_expert.gate_proj", |
| "model.layers.8.mlp.shared_expert.up_proj", |
| "model.layers.8.mlp.shared_expert_gate", |
| "model.layers.8.mlp.switch_mlp.down_proj", |
| "model.layers.8.mlp.switch_mlp.gate_proj", |
| "model.layers.8.mlp.switch_mlp.up_proj", |
| "model.layers.9.linear_attn.in_proj_ba", |
| "model.layers.9.linear_attn.in_proj_qkvz", |
| "model.layers.9.linear_attn.out_proj", |
| "model.layers.9.mlp.shared_expert.down_proj", |
| "model.layers.9.mlp.shared_expert.gate_proj", |
| "model.layers.9.mlp.shared_expert.up_proj", |
| "model.layers.9.mlp.shared_expert_gate", |
| "model.layers.9.mlp.switch_mlp.down_proj", |
| "model.layers.9.mlp.switch_mlp.gate_proj", |
| "model.layers.9.mlp.switch_mlp.up_proj" |
| ], |
| "missing": [ |
| "lm_head", |
| "model.embed_tokens" |
| ], |
| "mismatched": [], |
| "zero_count_experts": 3 |
| } |
