| { |
| "enabled": true, |
| "cache_path": "/Volumes/Models/models/Qwen/.oqe_imatrix/Qwen3-Embedding-8B-MLX-BF16-oQ8e-s128-l512.npz", |
| "cache_reused": true, |
| "entry_count": 252, |
| "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": 28, |
| "micro_batches": 5, |
| "batch_plan": { |
| "micro_batch_size": 28, |
| "estimated_sample_bytes": 8388608, |
| "capture_budget_bytes": 235304878, |
| "system_available_bytes": 23530487808, |
| "metal_available_bytes": 26796109276, |
| "live_available_bytes": 23530487808, |
| "hidden_size": 4096, |
| "num_experts": 0, |
| "top_k": 1 |
| }, |
| "processed_samples": 128, |
| "installed_modules": 252, |
| "capture_module_classes": { |
| "Linear": 252 |
| }, |
| "switch_capture_modules": 0, |
| "requires_expert_counts": false, |
| "coverage_sufficient": true, |
| "collection_sufficient": true, |
| "coverage": { |
| "has_expert_counts": false, |
| "expert_modules": 0, |
| "total_experts": 0, |
| "active_experts": 0, |
| "zero_count_experts": 0, |
| "active_ratio": 1.0, |
| "min_count": 0, |
| "p05_count": 0.0, |
| "p10_count": 0.0, |
| "median_count": 0.0, |
| "max_count": 0, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| }, |
| "rounds": [ |
| { |
| "processed_samples": 128, |
| "coverage_sufficient": true, |
| "collection_sufficient": true, |
| "coverage": { |
| "has_expert_counts": false, |
| "expert_modules": 0, |
| "total_experts": 0, |
| "active_experts": 0, |
| "zero_count_experts": 0, |
| "active_ratio": 1.0, |
| "min_count": 0, |
| "p05_count": 0.0, |
| "p10_count": 0.0, |
| "median_count": 0.0, |
| "max_count": 0, |
| "min_required_count": 16, |
| "required_percentile": 5 |
| } |
| } |
| ] |
| }, |
| "expert_coverage": { |
| "has_expert_counts": false, |
| "expert_modules": 0, |
| "total_experts": 0, |
| "active_experts": 0, |
| "zero_count_experts": 0, |
| "active_ratio": 1.0, |
| "min_count": 0, |
| "p05_count": 0.0, |
| "p10_count": 0.0, |
| "median_count": 0.0, |
| "max_count": 0, |
| "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.down_proj", |
| "model.layers.1.mlp.gate_proj", |
| "model.layers.1.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.down_proj", |
| "model.layers.10.mlp.gate_proj", |
| "model.layers.10.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.down_proj", |
| "model.layers.11.mlp.gate_proj", |
| "model.layers.11.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.down_proj", |
| "model.layers.12.mlp.gate_proj", |
| "model.layers.12.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.down_proj", |
| "model.layers.13.mlp.gate_proj", |
| "model.layers.13.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.down_proj", |
| "model.layers.14.mlp.gate_proj", |
| "model.layers.14.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.down_proj", |
| "model.layers.15.mlp.gate_proj", |
| "model.layers.15.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.down_proj", |
| "model.layers.16.mlp.gate_proj", |
| "model.layers.16.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.down_proj", |
| "model.layers.17.mlp.gate_proj", |
| "model.layers.17.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.down_proj", |
| "model.layers.18.mlp.gate_proj", |
| "model.layers.18.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.down_proj", |
| "model.layers.19.mlp.gate_proj", |
| "model.layers.19.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.down_proj", |
| "model.layers.2.mlp.gate_proj", |
| "model.layers.2.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.down_proj", |
| "model.layers.20.mlp.gate_proj", |
| "model.layers.20.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.down_proj", |
| "model.layers.21.mlp.gate_proj", |
| "model.layers.21.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.down_proj", |
| "model.layers.22.mlp.gate_proj", |
| "model.layers.22.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.down_proj", |
| "model.layers.23.mlp.gate_proj", |
| "model.layers.23.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.down_proj", |
| "model.layers.24.mlp.gate_proj", |
| "model.layers.24.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.down_proj", |
| "model.layers.25.mlp.gate_proj", |
| "model.layers.25.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.down_proj", |
| "model.layers.26.mlp.gate_proj", |
| "model.layers.26.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.down_proj", |
| "model.layers.27.mlp.gate_proj", |
| "model.layers.27.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.down_proj", |
| "model.layers.28.mlp.gate_proj", |
| "model.layers.28.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.down_proj", |
| "model.layers.29.mlp.gate_proj", |
| "model.layers.29.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.down_proj", |
| "model.layers.3.mlp.gate_proj", |
| "model.layers.3.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.down_proj", |
| "model.layers.30.mlp.gate_proj", |
| "model.layers.30.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.down_proj", |
| "model.layers.31.mlp.gate_proj", |
| "model.layers.31.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.down_proj", |
| "model.layers.32.mlp.gate_proj", |
| "model.layers.32.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.down_proj", |
| "model.layers.33.mlp.gate_proj", |
| "model.layers.33.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.down_proj", |
| "model.layers.34.mlp.gate_proj", |
| "model.layers.34.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.down_proj", |
| "model.layers.35.mlp.gate_proj", |
| "model.layers.35.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.4.mlp.down_proj", |
| "model.layers.4.mlp.gate_proj", |
| "model.layers.4.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.5.mlp.down_proj", |
| "model.layers.5.mlp.gate_proj", |
| "model.layers.5.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.6.mlp.down_proj", |
| "model.layers.6.mlp.gate_proj", |
| "model.layers.6.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.7.mlp.down_proj", |
| "model.layers.7.mlp.gate_proj", |
| "model.layers.7.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.mlp.down_proj", |
| "model.layers.8.mlp.gate_proj", |
| "model.layers.8.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.down_proj", |
| "model.layers.9.mlp.gate_proj", |
| "model.layers.9.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": [ |
| "model.embed_tokens" |
| ], |
| "mismatched": [], |
| "zero_count_experts": 0 |
| } |
