Darwin-4B-Genesis-oQ8e / oq_imatrix_report.json
brainworkup's picture
Upload Darwin-4B-Genesis-oQ8e via oMLX
986eb6b verified
Raw
History Blame Contribute Delete
21.4 kB
{
"enabled": true,
"cache_path": "/Users/joey/.omlx/models/.oqe_imatrix/Darwin-4B-Genesis-a7fc4f75c314-s128-l512.npz",
"cache_reused": true,
"entry_count": 210,
"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": 32,
"micro_batches": 4,
"batch_plan": {
"micro_batch_size": 32,
"estimated_sample_bytes": 5242880,
"capture_budget_bytes": 215900800,
"system_available_bytes": 25789005824,
"metal_available_bytes": 36117428438,
"live_available_bytes": 25789005824,
"model_bytes": 4198925799,
"remaining_available_bytes": 21590080025,
"fits_one_sample": true,
"hidden_size": 2560,
"num_experts": 0,
"top_k": 1
},
"processed_samples": 128,
"installed_modules": 343,
"capture_module_classes": {
"QuantizedLinear": 343
},
"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": [
"language_model.model.layers.0.mlp.down_proj",
"language_model.model.layers.0.mlp.gate_proj",
"language_model.model.layers.0.mlp.up_proj",
"language_model.model.layers.0.per_layer_input_gate",
"language_model.model.layers.0.self_attn.k_proj",
"language_model.model.layers.0.self_attn.o_proj",
"language_model.model.layers.0.self_attn.q_proj",
"language_model.model.layers.0.self_attn.v_proj",
"language_model.model.layers.1.mlp.down_proj",
"language_model.model.layers.1.mlp.gate_proj",
"language_model.model.layers.1.mlp.up_proj",
"language_model.model.layers.1.per_layer_input_gate",
"language_model.model.layers.1.self_attn.k_proj",
"language_model.model.layers.1.self_attn.o_proj",
"language_model.model.layers.1.self_attn.q_proj",
"language_model.model.layers.1.self_attn.v_proj",
"language_model.model.layers.10.mlp.down_proj",
"language_model.model.layers.10.mlp.gate_proj",
"language_model.model.layers.10.mlp.up_proj",
"language_model.model.layers.10.per_layer_input_gate",
"language_model.model.layers.10.self_attn.k_proj",
"language_model.model.layers.10.self_attn.o_proj",
"language_model.model.layers.10.self_attn.q_proj",
"language_model.model.layers.10.self_attn.v_proj",
"language_model.model.layers.11.mlp.down_proj",
"language_model.model.layers.11.mlp.gate_proj",
"language_model.model.layers.11.mlp.up_proj",
"language_model.model.layers.11.per_layer_input_gate",
"language_model.model.layers.11.self_attn.k_proj",
"language_model.model.layers.11.self_attn.o_proj",
"language_model.model.layers.11.self_attn.q_proj",
"language_model.model.layers.11.self_attn.v_proj",
"language_model.model.layers.12.mlp.down_proj",
"language_model.model.layers.12.mlp.gate_proj",
"language_model.model.layers.12.mlp.up_proj",
"language_model.model.layers.12.per_layer_input_gate",
"language_model.model.layers.12.self_attn.k_proj",
"language_model.model.layers.12.self_attn.o_proj",
"language_model.model.layers.12.self_attn.q_proj",
"language_model.model.layers.12.self_attn.v_proj",
"language_model.model.layers.13.mlp.down_proj",
"language_model.model.layers.13.mlp.gate_proj",
"language_model.model.layers.13.mlp.up_proj",
"language_model.model.layers.13.per_layer_input_gate",
"language_model.model.layers.13.self_attn.k_proj",
"language_model.model.layers.13.self_attn.o_proj",
"language_model.model.layers.13.self_attn.q_proj",
"language_model.model.layers.13.self_attn.v_proj",
"language_model.model.layers.14.mlp.down_proj",
"language_model.model.layers.14.mlp.gate_proj",
"language_model.model.layers.14.mlp.up_proj",
"language_model.model.layers.14.per_layer_input_gate",
"language_model.model.layers.14.self_attn.k_proj",
"language_model.model.layers.14.self_attn.o_proj",
"language_model.model.layers.14.self_attn.q_proj",
"language_model.model.layers.14.self_attn.v_proj",
"language_model.model.layers.15.mlp.down_proj",
"language_model.model.layers.15.mlp.gate_proj",
"language_model.model.layers.15.mlp.up_proj",
"language_model.model.layers.15.per_layer_input_gate",
"language_model.model.layers.15.self_attn.k_proj",
"language_model.model.layers.15.self_attn.o_proj",
"language_model.model.layers.15.self_attn.q_proj",
"language_model.model.layers.15.self_attn.v_proj",
"language_model.model.layers.16.mlp.down_proj",
"language_model.model.layers.16.mlp.gate_proj",
"language_model.model.layers.16.mlp.up_proj",
"language_model.model.layers.16.per_layer_input_gate",
"language_model.model.layers.16.self_attn.k_proj",
"language_model.model.layers.16.self_attn.o_proj",
"language_model.model.layers.16.self_attn.q_proj",
"language_model.model.layers.16.self_attn.v_proj",
"language_model.model.layers.17.mlp.down_proj",
"language_model.model.layers.17.mlp.gate_proj",
"language_model.model.layers.17.mlp.up_proj",
"language_model.model.layers.17.per_layer_input_gate",
"language_model.model.layers.17.self_attn.k_proj",
"language_model.model.layers.17.self_attn.o_proj",
"language_model.model.layers.17.self_attn.q_proj",
"language_model.model.layers.17.self_attn.v_proj",
"language_model.model.layers.18.mlp.down_proj",
"language_model.model.layers.18.mlp.gate_proj",
"language_model.model.layers.18.mlp.up_proj",
"language_model.model.layers.18.per_layer_input_gate",
"language_model.model.layers.18.self_attn.k_proj",
"language_model.model.layers.18.self_attn.o_proj",
"language_model.model.layers.18.self_attn.q_proj",
"language_model.model.layers.18.self_attn.v_proj",
"language_model.model.layers.19.mlp.down_proj",
"language_model.model.layers.19.mlp.gate_proj",
"language_model.model.layers.19.mlp.up_proj",
"language_model.model.layers.19.per_layer_input_gate",
"language_model.model.layers.19.self_attn.k_proj",
"language_model.model.layers.19.self_attn.o_proj",
"language_model.model.layers.19.self_attn.q_proj",
"language_model.model.layers.19.self_attn.v_proj",
"language_model.model.layers.2.mlp.down_proj",
"language_model.model.layers.2.mlp.gate_proj",
"language_model.model.layers.2.mlp.up_proj",
"language_model.model.layers.2.per_layer_input_gate",
"language_model.model.layers.2.self_attn.k_proj",
"language_model.model.layers.2.self_attn.o_proj",
"language_model.model.layers.2.self_attn.q_proj",
"language_model.model.layers.2.self_attn.v_proj",
"language_model.model.layers.20.mlp.down_proj",
"language_model.model.layers.20.mlp.gate_proj",
"language_model.model.layers.20.mlp.up_proj",
"language_model.model.layers.20.per_layer_input_gate",
"language_model.model.layers.20.self_attn.k_proj",
"language_model.model.layers.20.self_attn.o_proj",
"language_model.model.layers.20.self_attn.q_proj",
"language_model.model.layers.20.self_attn.v_proj",
"language_model.model.layers.21.mlp.down_proj",
"language_model.model.layers.21.mlp.gate_proj",
"language_model.model.layers.21.mlp.up_proj",
"language_model.model.layers.21.per_layer_input_gate",
"language_model.model.layers.21.self_attn.k_proj",
"language_model.model.layers.21.self_attn.o_proj",
"language_model.model.layers.21.self_attn.q_proj",
"language_model.model.layers.21.self_attn.v_proj",
"language_model.model.layers.22.mlp.down_proj",
"language_model.model.layers.22.mlp.gate_proj",
"language_model.model.layers.22.mlp.up_proj",
"language_model.model.layers.22.per_layer_input_gate",
"language_model.model.layers.22.self_attn.k_proj",
"language_model.model.layers.22.self_attn.o_proj",
"language_model.model.layers.22.self_attn.q_proj",
"language_model.model.layers.22.self_attn.v_proj",
"language_model.model.layers.23.mlp.down_proj",
"language_model.model.layers.23.mlp.gate_proj",
"language_model.model.layers.23.mlp.up_proj",
"language_model.model.layers.23.per_layer_input_gate",
"language_model.model.layers.23.self_attn.k_proj",
"language_model.model.layers.23.self_attn.o_proj",
"language_model.model.layers.23.self_attn.q_proj",
"language_model.model.layers.23.self_attn.v_proj",
"language_model.model.layers.24.self_attn.q_proj",
"language_model.model.layers.25.self_attn.q_proj",
"language_model.model.layers.26.self_attn.q_proj",
"language_model.model.layers.27.self_attn.q_proj",
"language_model.model.layers.28.self_attn.q_proj",
"language_model.model.layers.29.self_attn.q_proj",
"language_model.model.layers.3.mlp.down_proj",
"language_model.model.layers.3.mlp.gate_proj",
"language_model.model.layers.3.mlp.up_proj",
"language_model.model.layers.3.per_layer_input_gate",
"language_model.model.layers.3.self_attn.k_proj",
"language_model.model.layers.3.self_attn.o_proj",
"language_model.model.layers.3.self_attn.q_proj",
"language_model.model.layers.3.self_attn.v_proj",
"language_model.model.layers.30.self_attn.q_proj",
"language_model.model.layers.31.self_attn.q_proj",
"language_model.model.layers.32.self_attn.q_proj",
"language_model.model.layers.33.self_attn.q_proj",
"language_model.model.layers.34.self_attn.q_proj",
"language_model.model.layers.35.self_attn.q_proj",
"language_model.model.layers.36.self_attn.q_proj",
"language_model.model.layers.37.self_attn.q_proj",
"language_model.model.layers.38.self_attn.q_proj",
"language_model.model.layers.39.self_attn.q_proj",
"language_model.model.layers.4.mlp.down_proj",
"language_model.model.layers.4.mlp.gate_proj",
"language_model.model.layers.4.mlp.up_proj",
"language_model.model.layers.4.per_layer_input_gate",
"language_model.model.layers.4.self_attn.k_proj",
"language_model.model.layers.4.self_attn.o_proj",
"language_model.model.layers.4.self_attn.q_proj",
"language_model.model.layers.4.self_attn.v_proj",
"language_model.model.layers.40.self_attn.q_proj",
"language_model.model.layers.41.self_attn.q_proj",
"language_model.model.layers.5.mlp.down_proj",
"language_model.model.layers.5.mlp.gate_proj",
"language_model.model.layers.5.mlp.up_proj",
"language_model.model.layers.5.per_layer_input_gate",
"language_model.model.layers.5.self_attn.k_proj",
"language_model.model.layers.5.self_attn.o_proj",
"language_model.model.layers.5.self_attn.q_proj",
"language_model.model.layers.5.self_attn.v_proj",
"language_model.model.layers.6.mlp.down_proj",
"language_model.model.layers.6.mlp.gate_proj",
"language_model.model.layers.6.mlp.up_proj",
"language_model.model.layers.6.per_layer_input_gate",
"language_model.model.layers.6.self_attn.k_proj",
"language_model.model.layers.6.self_attn.o_proj",
"language_model.model.layers.6.self_attn.q_proj",
"language_model.model.layers.6.self_attn.v_proj",
"language_model.model.layers.7.mlp.down_proj",
"language_model.model.layers.7.mlp.gate_proj",
"language_model.model.layers.7.mlp.up_proj",
"language_model.model.layers.7.per_layer_input_gate",
"language_model.model.layers.7.self_attn.k_proj",
"language_model.model.layers.7.self_attn.o_proj",
"language_model.model.layers.7.self_attn.q_proj",
"language_model.model.layers.7.self_attn.v_proj",
"language_model.model.layers.8.mlp.down_proj",
"language_model.model.layers.8.mlp.gate_proj",
"language_model.model.layers.8.mlp.up_proj",
"language_model.model.layers.8.per_layer_input_gate",
"language_model.model.layers.8.self_attn.k_proj",
"language_model.model.layers.8.self_attn.o_proj",
"language_model.model.layers.8.self_attn.q_proj",
"language_model.model.layers.8.self_attn.v_proj",
"language_model.model.layers.9.mlp.down_proj",
"language_model.model.layers.9.mlp.gate_proj",
"language_model.model.layers.9.mlp.up_proj",
"language_model.model.layers.9.per_layer_input_gate",
"language_model.model.layers.9.self_attn.k_proj",
"language_model.model.layers.9.self_attn.o_proj",
"language_model.model.layers.9.self_attn.q_proj",
"language_model.model.layers.9.self_attn.v_proj"
],
"missing": [
"language_model.model.embed_tokens",
"language_model.model.embed_tokens_per_layer",
"language_model.model.layers.0.per_layer_projection",
"language_model.model.layers.1.per_layer_projection",
"language_model.model.layers.10.per_layer_projection",
"language_model.model.layers.11.per_layer_projection",
"language_model.model.layers.12.per_layer_projection",
"language_model.model.layers.13.per_layer_projection",
"language_model.model.layers.14.per_layer_projection",
"language_model.model.layers.15.per_layer_projection",
"language_model.model.layers.16.per_layer_projection",
"language_model.model.layers.17.per_layer_projection",
"language_model.model.layers.18.per_layer_projection",
"language_model.model.layers.19.per_layer_projection",
"language_model.model.layers.2.per_layer_projection",
"language_model.model.layers.20.per_layer_projection",
"language_model.model.layers.21.per_layer_projection",
"language_model.model.layers.22.per_layer_projection",
"language_model.model.layers.23.per_layer_projection",
"language_model.model.layers.24.mlp.down_proj",
"language_model.model.layers.24.mlp.gate_proj",
"language_model.model.layers.24.mlp.up_proj",
"language_model.model.layers.24.per_layer_input_gate",
"language_model.model.layers.24.per_layer_projection",
"language_model.model.layers.24.self_attn.o_proj",
"language_model.model.layers.25.mlp.down_proj",
"language_model.model.layers.25.mlp.gate_proj",
"language_model.model.layers.25.mlp.up_proj",
"language_model.model.layers.25.per_layer_input_gate",
"language_model.model.layers.25.per_layer_projection",
"language_model.model.layers.25.self_attn.o_proj",
"language_model.model.layers.26.mlp.down_proj",
"language_model.model.layers.26.mlp.gate_proj",
"language_model.model.layers.26.mlp.up_proj",
"language_model.model.layers.26.per_layer_input_gate",
"language_model.model.layers.26.per_layer_projection",
"language_model.model.layers.26.self_attn.o_proj",
"language_model.model.layers.27.mlp.down_proj",
"language_model.model.layers.27.mlp.gate_proj",
"language_model.model.layers.27.mlp.up_proj",
"language_model.model.layers.27.per_layer_input_gate",
"language_model.model.layers.27.per_layer_projection",
"language_model.model.layers.27.self_attn.o_proj",
"language_model.model.layers.28.mlp.down_proj",
"language_model.model.layers.28.mlp.gate_proj",
"language_model.model.layers.28.mlp.up_proj",
"language_model.model.layers.28.per_layer_input_gate",
"language_model.model.layers.28.per_layer_projection",
"language_model.model.layers.28.self_attn.o_proj",
"language_model.model.layers.29.mlp.down_proj",
"language_model.model.layers.29.mlp.gate_proj",
"language_model.model.layers.29.mlp.up_proj",
"language_model.model.layers.29.per_layer_input_gate",
"language_model.model.layers.29.per_layer_projection",
"language_model.model.layers.29.self_attn.o_proj",
"language_model.model.layers.3.per_layer_projection",
"language_model.model.layers.30.mlp.down_proj",
"language_model.model.layers.30.mlp.gate_proj",
"language_model.model.layers.30.mlp.up_proj",
"language_model.model.layers.30.per_layer_input_gate",
"language_model.model.layers.30.per_layer_projection",
"language_model.model.layers.30.self_attn.o_proj",
"language_model.model.layers.31.mlp.down_proj",
"language_model.model.layers.31.mlp.gate_proj",
"language_model.model.layers.31.mlp.up_proj",
"language_model.model.layers.31.per_layer_input_gate",
"language_model.model.layers.31.per_layer_projection",
"language_model.model.layers.31.self_attn.o_proj",
"language_model.model.layers.32.mlp.down_proj",
"language_model.model.layers.32.mlp.gate_proj",
"language_model.model.layers.32.mlp.up_proj",
"language_model.model.layers.32.per_layer_input_gate",
"language_model.model.layers.32.per_layer_projection",
"language_model.model.layers.32.self_attn.o_proj",
"language_model.model.layers.33.mlp.down_proj",
"language_model.model.layers.33.mlp.gate_proj",
"language_model.model.layers.33.mlp.up_proj",
"language_model.model.layers.33.per_layer_input_gate",
"language_model.model.layers.33.per_layer_projection",
"language_model.model.layers.33.self_attn.o_proj",
"language_model.model.layers.34.mlp.down_proj",
"language_model.model.layers.34.mlp.gate_proj",
"language_model.model.layers.34.mlp.up_proj",
"language_model.model.layers.34.per_layer_input_gate",
"language_model.model.layers.34.per_layer_projection",
"language_model.model.layers.34.self_attn.o_proj",
"language_model.model.layers.35.mlp.down_proj",
"language_model.model.layers.35.mlp.gate_proj",
"language_model.model.layers.35.mlp.up_proj",
"language_model.model.layers.35.per_layer_input_gate",
"language_model.model.layers.35.per_layer_projection",
"language_model.model.layers.35.self_attn.o_proj",
"language_model.model.layers.36.mlp.down_proj",
"language_model.model.layers.36.mlp.gate_proj",
"language_model.model.layers.36.mlp.up_proj",
"language_model.model.layers.36.per_layer_input_gate",
"language_model.model.layers.36.per_layer_projection",
"language_model.model.layers.36.self_attn.o_proj",
"language_model.model.layers.37.mlp.down_proj",
"language_model.model.layers.37.mlp.gate_proj",
"language_model.model.layers.37.mlp.up_proj",
"language_model.model.layers.37.per_layer_input_gate",
"language_model.model.layers.37.per_layer_projection",
"language_model.model.layers.37.self_attn.o_proj",
"language_model.model.layers.38.mlp.down_proj",
"language_model.model.layers.38.mlp.gate_proj",
"language_model.model.layers.38.mlp.up_proj",
"language_model.model.layers.38.per_layer_input_gate",
"language_model.model.layers.38.per_layer_projection",
"language_model.model.layers.38.self_attn.o_proj",
"language_model.model.layers.39.mlp.down_proj",
"language_model.model.layers.39.mlp.gate_proj",
"language_model.model.layers.39.mlp.up_proj",
"language_model.model.layers.39.per_layer_input_gate",
"language_model.model.layers.39.per_layer_projection",
"language_model.model.layers.39.self_attn.o_proj",
"language_model.model.layers.4.per_layer_projection",
"language_model.model.layers.40.mlp.down_proj",
"language_model.model.layers.40.mlp.gate_proj",
"language_model.model.layers.40.mlp.up_proj",
"language_model.model.layers.40.per_layer_input_gate",
"language_model.model.layers.40.per_layer_projection",
"language_model.model.layers.40.self_attn.o_proj",
"language_model.model.layers.41.mlp.down_proj",
"language_model.model.layers.41.mlp.gate_proj",
"language_model.model.layers.41.mlp.up_proj",
"language_model.model.layers.41.per_layer_input_gate",
"language_model.model.layers.41.per_layer_projection",
"language_model.model.layers.41.self_attn.o_proj",
"language_model.model.layers.5.per_layer_projection",
"language_model.model.layers.6.per_layer_projection",
"language_model.model.layers.7.per_layer_projection",
"language_model.model.layers.8.per_layer_projection",
"language_model.model.layers.9.per_layer_projection",
"language_model.model.per_layer_model_projection"
],
"mismatched": [],
"zero_count_experts": 0
}