{ "enabled": true, "cache_path": "/Users/robotta/omlx_models/max/.oqe_imatrix/MiniMax-M2.7-c14e4d1446dd-s128-l512.npz", "cache_reused": false, "entry_count": 496, "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": 50331648, "capture_budget_bytes": 805306368, "system_available_bytes": 536161353728, "metal_available_bytes": 547604240332, "live_available_bytes": 536161353728, "hidden_size": 3072, "num_experts": 256, "top_k": 8 }, "processed_samples": 1024, "installed_modules": 497, "capture_module_classes": { "Linear": 62, "QuantizedLinear": 249, "QuantizedSwitchLinear": 186 }, "switch_capture_modules": 186, "requires_expert_counts": true, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47604, "zero_count_experts": 12, "active_ratio": 0.9997479838709677, "min_count": 0, "p05_count": 6121.0, "p10_count": 7846.0, "median_count": 14766.5, "max_count": 238603, "min_required_count": 16, "required_percentile": 5 }, "rounds": [ { "processed_samples": 128, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47598, "zero_count_experts": 18, "active_ratio": 0.9996219758064516, "min_count": 0, "p05_count": 726.0, "p10_count": 939.0, "median_count": 1830.0, "max_count": 33934, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 256, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47598, "zero_count_experts": 18, "active_ratio": 0.9996219758064516, "min_count": 0, "p05_count": 1489.0, "p10_count": 1923.0, "median_count": 3670.0, "max_count": 66454, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 384, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47601, "zero_count_experts": 15, "active_ratio": 0.9996849798387096, "min_count": 0, "p05_count": 2217.0, "p10_count": 2871.0, "median_count": 5525.0, "max_count": 94545, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 512, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47601, "zero_count_experts": 15, "active_ratio": 0.9996849798387096, "min_count": 0, "p05_count": 3015.0, "p10_count": 3879.0, "median_count": 7374.0, "max_count": 120352, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 640, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47601, "zero_count_experts": 15, "active_ratio": 0.9996849798387096, "min_count": 0, "p05_count": 3758.0, "p10_count": 4849.0, "median_count": 9233.0, "max_count": 148910, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 768, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47601, "zero_count_experts": 15, "active_ratio": 0.9996849798387096, "min_count": 0, "p05_count": 4553.0, "p10_count": 5857.0, "median_count": 11063.5, "max_count": 178416, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 896, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47604, "zero_count_experts": 12, "active_ratio": 0.9997479838709677, "min_count": 0, "p05_count": 5319.0, "p10_count": 6837.0, "median_count": 12904.0, "max_count": 210082, "min_required_count": 16, "required_percentile": 5 } }, { "processed_samples": 1024, "coverage_sufficient": false, "collection_sufficient": false, "coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47604, "zero_count_experts": 12, "active_ratio": 0.9997479838709677, "min_count": 0, "p05_count": 6121.0, "p10_count": 7846.0, "median_count": 14766.5, "max_count": 238603, "min_required_count": 16, "required_percentile": 5 } } ] }, "expert_coverage": { "has_expert_counts": true, "expert_modules": 186, "total_experts": 47616, "active_experts": 47604, "zero_count_experts": 12, "active_ratio": 0.9997479838709677, "min_count": 0, "p05_count": 6121.0, "p10_count": 7846.0, "median_count": 14766.5, "max_count": 238603, "min_required_count": 16, "required_percentile": 5 }, "applied": [ "model.layers.0.block_sparse_moe.switch_mlp.down_proj", "model.layers.0.block_sparse_moe.switch_mlp.gate_proj", "model.layers.0.block_sparse_moe.switch_mlp.up_proj", "model.layers.0.self_attn.k_proj", "model.layers.0.self_attn.o_proj", "model.layers.0.self_attn.q_proj", "model.layers.0.self_attn.v_proj", "model.layers.1.block_sparse_moe.switch_mlp.down_proj", "model.layers.1.block_sparse_moe.switch_mlp.gate_proj", "model.layers.1.block_sparse_moe.switch_mlp.up_proj", "model.layers.1.self_attn.k_proj", "model.layers.1.self_attn.o_proj", "model.layers.1.self_attn.q_proj", "model.layers.1.self_attn.v_proj", "model.layers.10.block_sparse_moe.switch_mlp.down_proj", "model.layers.10.block_sparse_moe.switch_mlp.gate_proj", "model.layers.10.block_sparse_moe.switch_mlp.up_proj", "model.layers.10.self_attn.k_proj", "model.layers.10.self_attn.o_proj", "model.layers.10.self_attn.q_proj", "model.layers.10.self_attn.v_proj", "model.layers.11.block_sparse_moe.switch_mlp.down_proj", "model.layers.11.block_sparse_moe.switch_mlp.gate_proj", "model.layers.11.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.12.block_sparse_moe.switch_mlp.gate_proj", "model.layers.12.block_sparse_moe.switch_mlp.up_proj", "model.layers.12.self_attn.k_proj", "model.layers.12.self_attn.o_proj", "model.layers.12.self_attn.q_proj", "model.layers.12.self_attn.v_proj", "model.layers.13.block_sparse_moe.switch_mlp.down_proj", "model.layers.13.block_sparse_moe.switch_mlp.gate_proj", "model.layers.13.block_sparse_moe.switch_mlp.up_proj", "model.layers.13.self_attn.k_proj", "model.layers.13.self_attn.o_proj", "model.layers.13.self_attn.q_proj", "model.layers.13.self_attn.v_proj", "model.layers.14.block_sparse_moe.switch_mlp.down_proj", "model.layers.14.block_sparse_moe.switch_mlp.gate_proj", "model.layers.14.block_sparse_moe.switch_mlp.up_proj", "model.layers.14.self_attn.k_proj", "model.layers.14.self_attn.o_proj", "model.layers.14.self_attn.q_proj", "model.layers.14.self_attn.v_proj", "model.layers.15.block_sparse_moe.switch_mlp.down_proj", "model.layers.15.block_sparse_moe.switch_mlp.gate_proj", "model.layers.15.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.16.block_sparse_moe.switch_mlp.gate_proj", "model.layers.16.block_sparse_moe.switch_mlp.up_proj", "model.layers.16.self_attn.k_proj", "model.layers.16.self_attn.o_proj", "model.layers.16.self_attn.q_proj", "model.layers.16.self_attn.v_proj", "model.layers.17.block_sparse_moe.switch_mlp.down_proj", "model.layers.17.block_sparse_moe.switch_mlp.gate_proj", "model.layers.17.block_sparse_moe.switch_mlp.up_proj", "model.layers.17.self_attn.k_proj", "model.layers.17.self_attn.o_proj", "model.layers.17.self_attn.q_proj", "model.layers.17.self_attn.v_proj", "model.layers.18.block_sparse_moe.switch_mlp.down_proj", "model.layers.18.block_sparse_moe.switch_mlp.gate_proj", "model.layers.18.block_sparse_moe.switch_mlp.up_proj", "model.layers.18.self_attn.k_proj", "model.layers.18.self_attn.o_proj", "model.layers.18.self_attn.q_proj", "model.layers.18.self_attn.v_proj", "model.layers.19.block_sparse_moe.switch_mlp.down_proj", "model.layers.19.block_sparse_moe.switch_mlp.gate_proj", "model.layers.19.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.2.block_sparse_moe.switch_mlp.gate_proj", "model.layers.2.block_sparse_moe.switch_mlp.up_proj", "model.layers.2.self_attn.k_proj", "model.layers.2.self_attn.o_proj", "model.layers.2.self_attn.q_proj", "model.layers.2.self_attn.v_proj", "model.layers.20.block_sparse_moe.switch_mlp.down_proj", "model.layers.20.block_sparse_moe.switch_mlp.gate_proj", "model.layers.20.block_sparse_moe.switch_mlp.up_proj", "model.layers.20.self_attn.k_proj", "model.layers.20.self_attn.o_proj", "model.layers.20.self_attn.q_proj", "model.layers.20.self_attn.v_proj", "model.layers.21.block_sparse_moe.switch_mlp.down_proj", "model.layers.21.block_sparse_moe.switch_mlp.gate_proj", "model.layers.21.block_sparse_moe.switch_mlp.up_proj", "model.layers.21.self_attn.k_proj", "model.layers.21.self_attn.o_proj", "model.layers.21.self_attn.q_proj", "model.layers.21.self_attn.v_proj", "model.layers.22.block_sparse_moe.switch_mlp.down_proj", "model.layers.22.block_sparse_moe.switch_mlp.gate_proj", "model.layers.22.block_sparse_moe.switch_mlp.up_proj", "model.layers.22.self_attn.k_proj", "model.layers.22.self_attn.o_proj", "model.layers.22.self_attn.q_proj", "model.layers.22.self_attn.v_proj", "model.layers.23.block_sparse_moe.switch_mlp.down_proj", "model.layers.23.block_sparse_moe.switch_mlp.gate_proj", "model.layers.23.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.24.block_sparse_moe.switch_mlp.gate_proj", "model.layers.24.block_sparse_moe.switch_mlp.up_proj", "model.layers.24.self_attn.k_proj", "model.layers.24.self_attn.o_proj", "model.layers.24.self_attn.q_proj", "model.layers.24.self_attn.v_proj", "model.layers.25.block_sparse_moe.switch_mlp.down_proj", "model.layers.25.block_sparse_moe.switch_mlp.gate_proj", "model.layers.25.block_sparse_moe.switch_mlp.up_proj", "model.layers.25.self_attn.k_proj", "model.layers.25.self_attn.o_proj", "model.layers.25.self_attn.q_proj", "model.layers.25.self_attn.v_proj", "model.layers.26.block_sparse_moe.switch_mlp.down_proj", "model.layers.26.block_sparse_moe.switch_mlp.gate_proj", "model.layers.26.block_sparse_moe.switch_mlp.up_proj", "model.layers.26.self_attn.k_proj", "model.layers.26.self_attn.o_proj", "model.layers.26.self_attn.q_proj", "model.layers.26.self_attn.v_proj", "model.layers.27.block_sparse_moe.switch_mlp.down_proj", "model.layers.27.block_sparse_moe.switch_mlp.gate_proj", "model.layers.27.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.28.block_sparse_moe.switch_mlp.gate_proj", "model.layers.28.block_sparse_moe.switch_mlp.up_proj", "model.layers.28.self_attn.k_proj", "model.layers.28.self_attn.o_proj", "model.layers.28.self_attn.q_proj", "model.layers.28.self_attn.v_proj", "model.layers.29.block_sparse_moe.switch_mlp.down_proj", "model.layers.29.block_sparse_moe.switch_mlp.gate_proj", "model.layers.29.block_sparse_moe.switch_mlp.up_proj", "model.layers.29.self_attn.k_proj", "model.layers.29.self_attn.o_proj", "model.layers.29.self_attn.q_proj", "model.layers.29.self_attn.v_proj", "model.layers.3.block_sparse_moe.switch_mlp.down_proj", "model.layers.3.block_sparse_moe.switch_mlp.gate_proj", "model.layers.3.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.30.block_sparse_moe.switch_mlp.gate_proj", "model.layers.30.block_sparse_moe.switch_mlp.up_proj", "model.layers.30.self_attn.k_proj", "model.layers.30.self_attn.o_proj", "model.layers.30.self_attn.q_proj", "model.layers.30.self_attn.v_proj", "model.layers.31.block_sparse_moe.switch_mlp.down_proj", "model.layers.31.block_sparse_moe.switch_mlp.gate_proj", "model.layers.31.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.32.block_sparse_moe.switch_mlp.gate_proj", "model.layers.32.block_sparse_moe.switch_mlp.up_proj", "model.layers.32.self_attn.k_proj", "model.layers.32.self_attn.o_proj", "model.layers.32.self_attn.q_proj", "model.layers.32.self_attn.v_proj", "model.layers.33.block_sparse_moe.switch_mlp.down_proj", "model.layers.33.block_sparse_moe.switch_mlp.gate_proj", "model.layers.33.block_sparse_moe.switch_mlp.up_proj", "model.layers.33.self_attn.k_proj", "model.layers.33.self_attn.o_proj", "model.layers.33.self_attn.q_proj", "model.layers.33.self_attn.v_proj", "model.layers.34.block_sparse_moe.switch_mlp.down_proj", "model.layers.34.block_sparse_moe.switch_mlp.gate_proj", "model.layers.34.block_sparse_moe.switch_mlp.up_proj", "model.layers.34.self_attn.k_proj", "model.layers.34.self_attn.o_proj", "model.layers.34.self_attn.q_proj", "model.layers.34.self_attn.v_proj", "model.layers.35.block_sparse_moe.switch_mlp.down_proj", "model.layers.35.block_sparse_moe.switch_mlp.gate_proj", "model.layers.35.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.36.block_sparse_moe.switch_mlp.gate_proj", "model.layers.36.block_sparse_moe.switch_mlp.up_proj", "model.layers.36.self_attn.k_proj", "model.layers.36.self_attn.o_proj", "model.layers.36.self_attn.q_proj", "model.layers.36.self_attn.v_proj", "model.layers.37.block_sparse_moe.switch_mlp.down_proj", "model.layers.37.block_sparse_moe.switch_mlp.gate_proj", "model.layers.37.block_sparse_moe.switch_mlp.up_proj", "model.layers.37.self_attn.k_proj", "model.layers.37.self_attn.o_proj", "model.layers.37.self_attn.q_proj", "model.layers.37.self_attn.v_proj", "model.layers.38.block_sparse_moe.switch_mlp.down_proj", "model.layers.38.block_sparse_moe.switch_mlp.gate_proj", "model.layers.38.block_sparse_moe.switch_mlp.up_proj", "model.layers.38.self_attn.k_proj", "model.layers.38.self_attn.o_proj", "model.layers.38.self_attn.q_proj", "model.layers.38.self_attn.v_proj", "model.layers.39.block_sparse_moe.switch_mlp.down_proj", "model.layers.39.block_sparse_moe.switch_mlp.gate_proj", "model.layers.39.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.4.block_sparse_moe.switch_mlp.gate_proj", "model.layers.4.block_sparse_moe.switch_mlp.up_proj", "model.layers.4.self_attn.k_proj", "model.layers.4.self_attn.o_proj", "model.layers.4.self_attn.q_proj", "model.layers.4.self_attn.v_proj", "model.layers.40.block_sparse_moe.switch_mlp.down_proj", "model.layers.40.block_sparse_moe.switch_mlp.gate_proj", "model.layers.40.block_sparse_moe.switch_mlp.up_proj", "model.layers.40.self_attn.k_proj", "model.layers.40.self_attn.o_proj", "model.layers.40.self_attn.q_proj", "model.layers.40.self_attn.v_proj", "model.layers.41.block_sparse_moe.switch_mlp.down_proj", "model.layers.41.block_sparse_moe.switch_mlp.gate_proj", "model.layers.41.block_sparse_moe.switch_mlp.up_proj", "model.layers.41.self_attn.k_proj", "model.layers.41.self_attn.o_proj", "model.layers.41.self_attn.q_proj", "model.layers.41.self_attn.v_proj", "model.layers.42.block_sparse_moe.switch_mlp.down_proj", "model.layers.42.block_sparse_moe.switch_mlp.gate_proj", "model.layers.42.block_sparse_moe.switch_mlp.up_proj", "model.layers.42.self_attn.k_proj", "model.layers.42.self_attn.o_proj", "model.layers.42.self_attn.q_proj", "model.layers.42.self_attn.v_proj", "model.layers.43.block_sparse_moe.switch_mlp.down_proj", "model.layers.43.block_sparse_moe.switch_mlp.gate_proj", "model.layers.43.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.44.block_sparse_moe.switch_mlp.gate_proj", "model.layers.44.block_sparse_moe.switch_mlp.up_proj", "model.layers.44.self_attn.k_proj", "model.layers.44.self_attn.o_proj", "model.layers.44.self_attn.q_proj", "model.layers.44.self_attn.v_proj", "model.layers.45.block_sparse_moe.switch_mlp.down_proj", "model.layers.45.block_sparse_moe.switch_mlp.gate_proj", "model.layers.45.block_sparse_moe.switch_mlp.up_proj", "model.layers.45.self_attn.k_proj", "model.layers.45.self_attn.o_proj", "model.layers.45.self_attn.q_proj", "model.layers.45.self_attn.v_proj", "model.layers.46.block_sparse_moe.switch_mlp.down_proj", "model.layers.46.block_sparse_moe.switch_mlp.gate_proj", "model.layers.46.block_sparse_moe.switch_mlp.up_proj", "model.layers.46.self_attn.k_proj", "model.layers.46.self_attn.o_proj", "model.layers.46.self_attn.q_proj", "model.layers.46.self_attn.v_proj", "model.layers.47.block_sparse_moe.switch_mlp.down_proj", "model.layers.47.block_sparse_moe.switch_mlp.gate_proj", "model.layers.47.block_sparse_moe.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.48.block_sparse_moe.switch_mlp.down_proj", "model.layers.48.block_sparse_moe.switch_mlp.gate_proj", "model.layers.48.block_sparse_moe.switch_mlp.up_proj", "model.layers.48.self_attn.k_proj", "model.layers.48.self_attn.o_proj", "model.layers.48.self_attn.q_proj", "model.layers.48.self_attn.v_proj", "model.layers.49.block_sparse_moe.switch_mlp.down_proj", "model.layers.49.block_sparse_moe.switch_mlp.gate_proj", "model.layers.49.block_sparse_moe.switch_mlp.up_proj", "model.layers.49.self_attn.k_proj", "model.layers.49.self_attn.o_proj", "model.layers.49.self_attn.q_proj", "model.layers.49.self_attn.v_proj", "model.layers.5.block_sparse_moe.switch_mlp.down_proj", "model.layers.5.block_sparse_moe.switch_mlp.gate_proj", "model.layers.5.block_sparse_moe.switch_mlp.up_proj", "model.layers.5.self_attn.k_proj", "model.layers.5.self_attn.o_proj", "model.layers.5.self_attn.q_proj", "model.layers.5.self_attn.v_proj", "model.layers.50.block_sparse_moe.switch_mlp.down_proj", "model.layers.50.block_sparse_moe.switch_mlp.gate_proj", "model.layers.50.block_sparse_moe.switch_mlp.up_proj", "model.layers.50.self_attn.k_proj", "model.layers.50.self_attn.o_proj", "model.layers.50.self_attn.q_proj", "model.layers.50.self_attn.v_proj", "model.layers.51.block_sparse_moe.switch_mlp.down_proj", "model.layers.51.block_sparse_moe.switch_mlp.gate_proj", "model.layers.51.block_sparse_moe.switch_mlp.up_proj", "model.layers.51.self_attn.k_proj", "model.layers.51.self_attn.o_proj", "model.layers.51.self_attn.q_proj", "model.layers.51.self_attn.v_proj", "model.layers.52.block_sparse_moe.switch_mlp.down_proj", "model.layers.52.block_sparse_moe.switch_mlp.gate_proj", "model.layers.52.block_sparse_moe.switch_mlp.up_proj", "model.layers.52.self_attn.k_proj", "model.layers.52.self_attn.o_proj", "model.layers.52.self_attn.q_proj", "model.layers.52.self_attn.v_proj", "model.layers.53.block_sparse_moe.switch_mlp.down_proj", "model.layers.53.block_sparse_moe.switch_mlp.gate_proj", "model.layers.53.block_sparse_moe.switch_mlp.up_proj", "model.layers.53.self_attn.k_proj", "model.layers.53.self_attn.o_proj", "model.layers.53.self_attn.q_proj", "model.layers.53.self_attn.v_proj", "model.layers.54.block_sparse_moe.switch_mlp.down_proj", "model.layers.54.block_sparse_moe.switch_mlp.gate_proj", "model.layers.54.block_sparse_moe.switch_mlp.up_proj", "model.layers.54.self_attn.k_proj", "model.layers.54.self_attn.o_proj", "model.layers.54.self_attn.q_proj", "model.layers.54.self_attn.v_proj", "model.layers.55.block_sparse_moe.switch_mlp.down_proj", "model.layers.55.block_sparse_moe.switch_mlp.gate_proj", "model.layers.55.block_sparse_moe.switch_mlp.up_proj", "model.layers.55.self_attn.k_proj", "model.layers.55.self_attn.o_proj", "model.layers.55.self_attn.q_proj", "model.layers.55.self_attn.v_proj", "model.layers.56.block_sparse_moe.switch_mlp.down_proj", "model.layers.56.block_sparse_moe.switch_mlp.gate_proj", "model.layers.56.block_sparse_moe.switch_mlp.up_proj", "model.layers.56.self_attn.k_proj", "model.layers.56.self_attn.o_proj", "model.layers.56.self_attn.q_proj", "model.layers.56.self_attn.v_proj", "model.layers.57.block_sparse_moe.switch_mlp.down_proj", "model.layers.57.block_sparse_moe.switch_mlp.gate_proj", "model.layers.57.block_sparse_moe.switch_mlp.up_proj", "model.layers.57.self_attn.k_proj", "model.layers.57.self_attn.o_proj", "model.layers.57.self_attn.q_proj", "model.layers.57.self_attn.v_proj", "model.layers.58.block_sparse_moe.switch_mlp.down_proj", "model.layers.58.block_sparse_moe.switch_mlp.gate_proj", "model.layers.58.block_sparse_moe.switch_mlp.up_proj", "model.layers.58.self_attn.k_proj", "model.layers.58.self_attn.o_proj", "model.layers.58.self_attn.q_proj", "model.layers.58.self_attn.v_proj", "model.layers.59.block_sparse_moe.switch_mlp.down_proj", "model.layers.59.block_sparse_moe.switch_mlp.gate_proj", "model.layers.59.block_sparse_moe.switch_mlp.up_proj", "model.layers.59.self_attn.k_proj", "model.layers.59.self_attn.o_proj", "model.layers.59.self_attn.q_proj", "model.layers.59.self_attn.v_proj", "model.layers.6.block_sparse_moe.switch_mlp.down_proj", "model.layers.6.block_sparse_moe.switch_mlp.gate_proj", "model.layers.6.block_sparse_moe.switch_mlp.up_proj", "model.layers.6.self_attn.k_proj", "model.layers.6.self_attn.o_proj", "model.layers.6.self_attn.q_proj", "model.layers.6.self_attn.v_proj", "model.layers.60.block_sparse_moe.switch_mlp.down_proj", "model.layers.60.block_sparse_moe.switch_mlp.gate_proj", "model.layers.60.block_sparse_moe.switch_mlp.up_proj", "model.layers.60.self_attn.k_proj", "model.layers.60.self_attn.o_proj", "model.layers.60.self_attn.q_proj", "model.layers.60.self_attn.v_proj", "model.layers.61.block_sparse_moe.switch_mlp.down_proj", "model.layers.61.block_sparse_moe.switch_mlp.gate_proj", "model.layers.61.block_sparse_moe.switch_mlp.up_proj", "model.layers.61.self_attn.k_proj", "model.layers.61.self_attn.o_proj", "model.layers.61.self_attn.q_proj", "model.layers.61.self_attn.v_proj", "model.layers.7.block_sparse_moe.switch_mlp.down_proj", "model.layers.7.block_sparse_moe.switch_mlp.gate_proj", "model.layers.7.block_sparse_moe.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.block_sparse_moe.switch_mlp.down_proj", "model.layers.8.block_sparse_moe.switch_mlp.gate_proj", "model.layers.8.block_sparse_moe.switch_mlp.up_proj", "model.layers.8.self_attn.k_proj", "model.layers.8.self_attn.o_proj", "model.layers.8.self_attn.q_proj", "model.layers.8.self_attn.v_proj", "model.layers.9.block_sparse_moe.switch_mlp.down_proj", "model.layers.9.block_sparse_moe.switch_mlp.gate_proj", "model.layers.9.block_sparse_moe.switch_mlp.up_proj", "model.layers.9.self_attn.k_proj", "model.layers.9.self_attn.o_proj", "model.layers.9.self_attn.q_proj", "model.layers.9.self_attn.v_proj" ], "missing": [ "lm_head", "model.embed_tokens" ], "mismatched": [], "zero_count_experts": 12 }