{ "enabled": true, "cache_path": "/Users/gabfssilva/.cache/huggingface/hub/models--local--Hy3-mlx-oQ2e/snapshots/.oqe_imatrix/f25e17585fa97688711042f822a8bedf975fb80e-oQe-s128-l512.npz", "cache_reused": true, "entry_count": 876, "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": 12, "micro_batches": 11, "batch_plan": { "micro_batch_size": 12, "estimated_sample_bytes": 67108864, "capture_budget_bytes": 805306368, "system_available_bytes": 116966981632, "metal_available_bytes": 115444302520, "live_available_bytes": 115444302520, "hidden_size": 4096, "num_experts": 192, "top_k": 8 }, "processed_samples": 128, "installed_modules": 877, "capture_module_classes": { "Linear": 79, "QuantizedLinear": 561, "QuantizedSwitchLinear": 237 }, "switch_capture_modules": 237, "requires_expert_counts": true, "coverage_sufficient": true, "collection_sufficient": true, "coverage": { "has_expert_counts": true, "expert_modules": 237, "total_experts": 45504, "active_experts": 45504, "zero_count_experts": 0, "active_ratio": 1.0, "min_count": 24, "p05_count": 1045.0, "p10_count": 1331.0, "median_count": 2472.0, "max_count": 24939, "min_required_count": 16, "required_percentile": 5 }, "rounds": [ { "processed_samples": 128, "coverage_sufficient": true, "collection_sufficient": true, "coverage": { "has_expert_counts": true, "expert_modules": 237, "total_experts": 45504, "active_experts": 45504, "zero_count_experts": 0, "active_ratio": 1.0, "min_count": 24, "p05_count": 1045.0, "p10_count": 1331.0, "median_count": 2472.0, "max_count": 24939, "min_required_count": 16, "required_percentile": 5 } } ] }, "expert_coverage": { "has_expert_counts": true, "expert_modules": 237, "total_experts": 45504, "active_experts": 45504, "zero_count_experts": 0, "active_ratio": 1.0, "min_count": 24, "p05_count": 1045.0, "p10_count": 1331.0, "median_count": 2472.0, "max_count": 24939, "min_required_count": 16, "required_percentile": 5 }, "applied": [ "model.layers.0.mlp.down_proj", "model.layers.0.mlp.gate_proj", "model.layers.0.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.mlp.shared_mlp.down_proj", "model.layers.1.mlp.shared_mlp.gate_proj", "model.layers.1.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.10.mlp.shared_mlp.gate_proj", "model.layers.10.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.11.mlp.shared_mlp.gate_proj", "model.layers.11.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.12.mlp.shared_mlp.gate_proj", "model.layers.12.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.13.mlp.shared_mlp.gate_proj", "model.layers.13.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.14.mlp.shared_mlp.gate_proj", "model.layers.14.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.15.mlp.shared_mlp.gate_proj", "model.layers.15.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.16.mlp.shared_mlp.gate_proj", "model.layers.16.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.17.mlp.shared_mlp.gate_proj", "model.layers.17.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.18.mlp.shared_mlp.gate_proj", "model.layers.18.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.19.mlp.shared_mlp.gate_proj", "model.layers.19.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.2.mlp.shared_mlp.gate_proj", "model.layers.2.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.20.mlp.shared_mlp.gate_proj", "model.layers.20.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.21.mlp.shared_mlp.gate_proj", "model.layers.21.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.22.mlp.shared_mlp.gate_proj", "model.layers.22.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.23.mlp.shared_mlp.gate_proj", "model.layers.23.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.24.mlp.shared_mlp.gate_proj", "model.layers.24.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.25.mlp.shared_mlp.gate_proj", "model.layers.25.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.26.mlp.shared_mlp.gate_proj", "model.layers.26.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.27.mlp.shared_mlp.gate_proj", "model.layers.27.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.28.mlp.shared_mlp.gate_proj", "model.layers.28.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.29.mlp.shared_mlp.gate_proj", "model.layers.29.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.3.mlp.shared_mlp.gate_proj", "model.layers.3.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.30.mlp.shared_mlp.gate_proj", "model.layers.30.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.31.mlp.shared_mlp.gate_proj", "model.layers.31.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.32.mlp.shared_mlp.gate_proj", "model.layers.32.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.33.mlp.shared_mlp.gate_proj", "model.layers.33.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.34.mlp.shared_mlp.gate_proj", "model.layers.34.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.35.mlp.shared_mlp.gate_proj", "model.layers.35.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.36.mlp.shared_mlp.gate_proj", "model.layers.36.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.37.mlp.shared_mlp.gate_proj", "model.layers.37.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.38.mlp.shared_mlp.gate_proj", "model.layers.38.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.39.mlp.shared_mlp.gate_proj", "model.layers.39.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.4.mlp.shared_mlp.gate_proj", "model.layers.4.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.40.mlp.shared_mlp.gate_proj", "model.layers.40.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.41.mlp.shared_mlp.gate_proj", "model.layers.41.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.42.mlp.shared_mlp.gate_proj", "model.layers.42.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.43.mlp.shared_mlp.gate_proj", "model.layers.43.mlp.shared_mlp.up_proj", "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.mlp.shared_mlp.down_proj", "model.layers.44.mlp.shared_mlp.gate_proj", "model.layers.44.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.45.mlp.shared_mlp.gate_proj", "model.layers.45.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.46.mlp.shared_mlp.gate_proj", "model.layers.46.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.47.mlp.shared_mlp.gate_proj", "model.layers.47.mlp.shared_mlp.up_proj", "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.48.mlp.shared_mlp.down_proj", "model.layers.48.mlp.shared_mlp.gate_proj", "model.layers.48.mlp.shared_mlp.up_proj", "model.layers.48.mlp.switch_mlp.down_proj", "model.layers.48.mlp.switch_mlp.gate_proj", "model.layers.48.mlp.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.mlp.shared_mlp.down_proj", "model.layers.49.mlp.shared_mlp.gate_proj", "model.layers.49.mlp.shared_mlp.up_proj", "model.layers.49.mlp.switch_mlp.down_proj", "model.layers.49.mlp.switch_mlp.gate_proj", "model.layers.49.mlp.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.mlp.shared_mlp.down_proj", "model.layers.5.mlp.shared_mlp.gate_proj", "model.layers.5.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.50.mlp.shared_mlp.gate_proj", "model.layers.50.mlp.shared_mlp.up_proj", "model.layers.50.mlp.switch_mlp.down_proj", "model.layers.50.mlp.switch_mlp.gate_proj", "model.layers.50.mlp.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.mlp.shared_mlp.down_proj", "model.layers.51.mlp.shared_mlp.gate_proj", "model.layers.51.mlp.shared_mlp.up_proj", "model.layers.51.mlp.switch_mlp.down_proj", "model.layers.51.mlp.switch_mlp.gate_proj", "model.layers.51.mlp.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.mlp.shared_mlp.down_proj", "model.layers.52.mlp.shared_mlp.gate_proj", "model.layers.52.mlp.shared_mlp.up_proj", "model.layers.52.mlp.switch_mlp.down_proj", "model.layers.52.mlp.switch_mlp.gate_proj", "model.layers.52.mlp.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.mlp.shared_mlp.down_proj", "model.layers.53.mlp.shared_mlp.gate_proj", "model.layers.53.mlp.shared_mlp.up_proj", "model.layers.53.mlp.switch_mlp.down_proj", "model.layers.53.mlp.switch_mlp.gate_proj", "model.layers.53.mlp.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.mlp.shared_mlp.down_proj", "model.layers.54.mlp.shared_mlp.gate_proj", "model.layers.54.mlp.shared_mlp.up_proj", "model.layers.54.mlp.switch_mlp.down_proj", "model.layers.54.mlp.switch_mlp.gate_proj", "model.layers.54.mlp.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.mlp.shared_mlp.down_proj", "model.layers.55.mlp.shared_mlp.gate_proj", "model.layers.55.mlp.shared_mlp.up_proj", "model.layers.55.mlp.switch_mlp.down_proj", "model.layers.55.mlp.switch_mlp.gate_proj", "model.layers.55.mlp.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.mlp.shared_mlp.down_proj", "model.layers.56.mlp.shared_mlp.gate_proj", "model.layers.56.mlp.shared_mlp.up_proj", "model.layers.56.mlp.switch_mlp.down_proj", "model.layers.56.mlp.switch_mlp.gate_proj", "model.layers.56.mlp.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.mlp.shared_mlp.down_proj", "model.layers.57.mlp.shared_mlp.gate_proj", "model.layers.57.mlp.shared_mlp.up_proj", "model.layers.57.mlp.switch_mlp.down_proj", "model.layers.57.mlp.switch_mlp.gate_proj", "model.layers.57.mlp.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.mlp.shared_mlp.down_proj", "model.layers.58.mlp.shared_mlp.gate_proj", "model.layers.58.mlp.shared_mlp.up_proj", "model.layers.58.mlp.switch_mlp.down_proj", "model.layers.58.mlp.switch_mlp.gate_proj", "model.layers.58.mlp.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.mlp.shared_mlp.down_proj", "model.layers.59.mlp.shared_mlp.gate_proj", "model.layers.59.mlp.shared_mlp.up_proj", "model.layers.59.mlp.switch_mlp.down_proj", "model.layers.59.mlp.switch_mlp.gate_proj", "model.layers.59.mlp.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.mlp.shared_mlp.down_proj", "model.layers.6.mlp.shared_mlp.gate_proj", "model.layers.6.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.60.mlp.shared_mlp.gate_proj", "model.layers.60.mlp.shared_mlp.up_proj", "model.layers.60.mlp.switch_mlp.down_proj", "model.layers.60.mlp.switch_mlp.gate_proj", "model.layers.60.mlp.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.mlp.shared_mlp.down_proj", "model.layers.61.mlp.shared_mlp.gate_proj", "model.layers.61.mlp.shared_mlp.up_proj", "model.layers.61.mlp.switch_mlp.down_proj", "model.layers.61.mlp.switch_mlp.gate_proj", "model.layers.61.mlp.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.62.mlp.shared_mlp.down_proj", "model.layers.62.mlp.shared_mlp.gate_proj", "model.layers.62.mlp.shared_mlp.up_proj", "model.layers.62.mlp.switch_mlp.down_proj", "model.layers.62.mlp.switch_mlp.gate_proj", "model.layers.62.mlp.switch_mlp.up_proj", "model.layers.62.self_attn.k_proj", "model.layers.62.self_attn.o_proj", "model.layers.62.self_attn.q_proj", "model.layers.62.self_attn.v_proj", "model.layers.63.mlp.shared_mlp.down_proj", "model.layers.63.mlp.shared_mlp.gate_proj", "model.layers.63.mlp.shared_mlp.up_proj", "model.layers.63.mlp.switch_mlp.down_proj", "model.layers.63.mlp.switch_mlp.gate_proj", "model.layers.63.mlp.switch_mlp.up_proj", "model.layers.63.self_attn.k_proj", "model.layers.63.self_attn.o_proj", "model.layers.63.self_attn.q_proj", "model.layers.63.self_attn.v_proj", "model.layers.64.mlp.shared_mlp.down_proj", "model.layers.64.mlp.shared_mlp.gate_proj", "model.layers.64.mlp.shared_mlp.up_proj", "model.layers.64.mlp.switch_mlp.down_proj", "model.layers.64.mlp.switch_mlp.gate_proj", "model.layers.64.mlp.switch_mlp.up_proj", "model.layers.64.self_attn.k_proj", "model.layers.64.self_attn.o_proj", "model.layers.64.self_attn.q_proj", "model.layers.64.self_attn.v_proj", "model.layers.65.mlp.shared_mlp.down_proj", "model.layers.65.mlp.shared_mlp.gate_proj", "model.layers.65.mlp.shared_mlp.up_proj", "model.layers.65.mlp.switch_mlp.down_proj", "model.layers.65.mlp.switch_mlp.gate_proj", "model.layers.65.mlp.switch_mlp.up_proj", "model.layers.65.self_attn.k_proj", "model.layers.65.self_attn.o_proj", "model.layers.65.self_attn.q_proj", "model.layers.65.self_attn.v_proj", "model.layers.66.mlp.shared_mlp.down_proj", "model.layers.66.mlp.shared_mlp.gate_proj", "model.layers.66.mlp.shared_mlp.up_proj", "model.layers.66.mlp.switch_mlp.down_proj", "model.layers.66.mlp.switch_mlp.gate_proj", "model.layers.66.mlp.switch_mlp.up_proj", "model.layers.66.self_attn.k_proj", "model.layers.66.self_attn.o_proj", "model.layers.66.self_attn.q_proj", "model.layers.66.self_attn.v_proj", "model.layers.67.mlp.shared_mlp.down_proj", "model.layers.67.mlp.shared_mlp.gate_proj", "model.layers.67.mlp.shared_mlp.up_proj", "model.layers.67.mlp.switch_mlp.down_proj", "model.layers.67.mlp.switch_mlp.gate_proj", "model.layers.67.mlp.switch_mlp.up_proj", "model.layers.67.self_attn.k_proj", "model.layers.67.self_attn.o_proj", "model.layers.67.self_attn.q_proj", "model.layers.67.self_attn.v_proj", "model.layers.68.mlp.shared_mlp.down_proj", "model.layers.68.mlp.shared_mlp.gate_proj", "model.layers.68.mlp.shared_mlp.up_proj", "model.layers.68.mlp.switch_mlp.down_proj", "model.layers.68.mlp.switch_mlp.gate_proj", "model.layers.68.mlp.switch_mlp.up_proj", "model.layers.68.self_attn.k_proj", "model.layers.68.self_attn.o_proj", "model.layers.68.self_attn.q_proj", "model.layers.68.self_attn.v_proj", "model.layers.69.mlp.shared_mlp.down_proj", "model.layers.69.mlp.shared_mlp.gate_proj", "model.layers.69.mlp.shared_mlp.up_proj", "model.layers.69.mlp.switch_mlp.down_proj", "model.layers.69.mlp.switch_mlp.gate_proj", "model.layers.69.mlp.switch_mlp.up_proj", "model.layers.69.self_attn.k_proj", "model.layers.69.self_attn.o_proj", "model.layers.69.self_attn.q_proj", "model.layers.69.self_attn.v_proj", "model.layers.7.mlp.shared_mlp.down_proj", "model.layers.7.mlp.shared_mlp.gate_proj", "model.layers.7.mlp.shared_mlp.up_proj", "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.70.mlp.shared_mlp.down_proj", "model.layers.70.mlp.shared_mlp.gate_proj", "model.layers.70.mlp.shared_mlp.up_proj", "model.layers.70.mlp.switch_mlp.down_proj", "model.layers.70.mlp.switch_mlp.gate_proj", "model.layers.70.mlp.switch_mlp.up_proj", "model.layers.70.self_attn.k_proj", "model.layers.70.self_attn.o_proj", "model.layers.70.self_attn.q_proj", "model.layers.70.self_attn.v_proj", "model.layers.71.mlp.shared_mlp.down_proj", "model.layers.71.mlp.shared_mlp.gate_proj", "model.layers.71.mlp.shared_mlp.up_proj", "model.layers.71.mlp.switch_mlp.down_proj", "model.layers.71.mlp.switch_mlp.gate_proj", "model.layers.71.mlp.switch_mlp.up_proj", "model.layers.71.self_attn.k_proj", "model.layers.71.self_attn.o_proj", "model.layers.71.self_attn.q_proj", "model.layers.71.self_attn.v_proj", "model.layers.72.mlp.shared_mlp.down_proj", "model.layers.72.mlp.shared_mlp.gate_proj", "model.layers.72.mlp.shared_mlp.up_proj", "model.layers.72.mlp.switch_mlp.down_proj", "model.layers.72.mlp.switch_mlp.gate_proj", "model.layers.72.mlp.switch_mlp.up_proj", "model.layers.72.self_attn.k_proj", "model.layers.72.self_attn.o_proj", "model.layers.72.self_attn.q_proj", "model.layers.72.self_attn.v_proj", "model.layers.73.mlp.shared_mlp.down_proj", "model.layers.73.mlp.shared_mlp.gate_proj", "model.layers.73.mlp.shared_mlp.up_proj", "model.layers.73.mlp.switch_mlp.down_proj", "model.layers.73.mlp.switch_mlp.gate_proj", "model.layers.73.mlp.switch_mlp.up_proj", "model.layers.73.self_attn.k_proj", "model.layers.73.self_attn.o_proj", "model.layers.73.self_attn.q_proj", "model.layers.73.self_attn.v_proj", "model.layers.74.mlp.shared_mlp.down_proj", "model.layers.74.mlp.shared_mlp.gate_proj", "model.layers.74.mlp.shared_mlp.up_proj", "model.layers.74.mlp.switch_mlp.down_proj", "model.layers.74.mlp.switch_mlp.gate_proj", "model.layers.74.mlp.switch_mlp.up_proj", "model.layers.74.self_attn.k_proj", "model.layers.74.self_attn.o_proj", "model.layers.74.self_attn.q_proj", "model.layers.74.self_attn.v_proj", "model.layers.75.mlp.shared_mlp.down_proj", "model.layers.75.mlp.shared_mlp.gate_proj", "model.layers.75.mlp.shared_mlp.up_proj", "model.layers.75.mlp.switch_mlp.down_proj", "model.layers.75.mlp.switch_mlp.gate_proj", "model.layers.75.mlp.switch_mlp.up_proj", "model.layers.75.self_attn.k_proj", "model.layers.75.self_attn.o_proj", "model.layers.75.self_attn.q_proj", "model.layers.75.self_attn.v_proj", "model.layers.76.mlp.shared_mlp.down_proj", "model.layers.76.mlp.shared_mlp.gate_proj", "model.layers.76.mlp.shared_mlp.up_proj", "model.layers.76.mlp.switch_mlp.down_proj", "model.layers.76.mlp.switch_mlp.gate_proj", "model.layers.76.mlp.switch_mlp.up_proj", "model.layers.76.self_attn.k_proj", "model.layers.76.self_attn.o_proj", "model.layers.76.self_attn.q_proj", "model.layers.76.self_attn.v_proj", "model.layers.77.mlp.shared_mlp.down_proj", "model.layers.77.mlp.shared_mlp.gate_proj", "model.layers.77.mlp.shared_mlp.up_proj", "model.layers.77.mlp.switch_mlp.down_proj", "model.layers.77.mlp.switch_mlp.gate_proj", "model.layers.77.mlp.switch_mlp.up_proj", "model.layers.77.self_attn.k_proj", "model.layers.77.self_attn.o_proj", "model.layers.77.self_attn.q_proj", "model.layers.77.self_attn.v_proj", "model.layers.78.mlp.shared_mlp.down_proj", "model.layers.78.mlp.shared_mlp.gate_proj", "model.layers.78.mlp.shared_mlp.up_proj", "model.layers.78.mlp.switch_mlp.down_proj", "model.layers.78.mlp.switch_mlp.gate_proj", "model.layers.78.mlp.switch_mlp.up_proj", "model.layers.78.self_attn.k_proj", "model.layers.78.self_attn.o_proj", "model.layers.78.self_attn.q_proj", "model.layers.78.self_attn.v_proj", "model.layers.79.mlp.shared_mlp.down_proj", "model.layers.79.mlp.shared_mlp.gate_proj", "model.layers.79.mlp.shared_mlp.up_proj", "model.layers.79.mlp.switch_mlp.down_proj", "model.layers.79.mlp.switch_mlp.gate_proj", "model.layers.79.mlp.switch_mlp.up_proj", "model.layers.79.self_attn.k_proj", "model.layers.79.self_attn.o_proj", "model.layers.79.self_attn.q_proj", "model.layers.79.self_attn.v_proj", "model.layers.8.mlp.shared_mlp.down_proj", "model.layers.8.mlp.shared_mlp.gate_proj", "model.layers.8.mlp.shared_mlp.up_proj", "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.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.mlp.shared_mlp.down_proj", "model.layers.9.mlp.shared_mlp.gate_proj", "model.layers.9.mlp.shared_mlp.up_proj", "model.layers.9.mlp.switch_mlp.down_proj", "model.layers.9.mlp.switch_mlp.gate_proj", "model.layers.9.mlp.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": 0 }