K2-Horizon-MoVA-36B-A4B-oQ4e / oq_imatrix_report.json
hermitdave's picture
Add files using upload-large-folder tool
5552846 verified
Raw
History Blame Contribute Delete
32.9 kB
{
"enabled": true,
"cache_path": "/Users/hermit.dave/Projects/ml/models/.oqe_imatrix/K2-Horizon-MoVA-36B-A4B-oQe-s128-l512.npz",
"cache_reused": false,
"entry_count": 609,
"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": 5,
"micro_batches": 208,
"batch_plan": {
"micro_batch_size": 5,
"estimated_sample_bytes": 41943040,
"capture_budget_bytes": 221469698,
"system_available_bytes": 43226824704,
"metal_available_bytes": 55658402428,
"live_available_bytes": 43226824704,
"model_bytes": 21079854889,
"remaining_available_bytes": 22146969815,
"fits_one_sample": true,
"hidden_size": 2560,
"num_experts": 100,
"top_k": 8,
"gemma4_state_bytes": 0,
"num_hidden_layers": 48,
"num_kv_shared_layers": 0,
"per_layer_input_size": 0
},
"processed_samples": 1024,
"model_class": "k2_horizon.Model",
"layer_model_class": "k2_horizon.K2HorizonModel",
"layer_model_type": "k2_horizon",
"layer_count": 48,
"layer_state_kind": "generic",
"successful_layer_forwards": 9984,
"skipped_layer_forwards": 0,
"mtp_head_forwards": 0,
"installed_modules": 610,
"capture_module_classes": {
"Linear": 45,
"QuantizedLinear": 385,
"QuantizedSwitchLinear": 180
},
"switch_capture_modules": 180,
"requires_expert_counts": true,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15883,
"zero_count_experts": 497,
"active_ratio": 0.9696581196581197,
"min_count": 0,
"p05_count": 8.0,
"p10_count": 2428.900000000001,
"median_count": 23935.0,
"max_count": 524288,
"min_required_count": 16,
"required_percentile": 5
},
"rounds": [
{
"processed_samples": 128,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15623,
"zero_count_experts": 757,
"active_ratio": 0.9537851037851038,
"min_count": 0,
"p05_count": 1.0,
"p10_count": 311.0,
"median_count": 3098.0,
"max_count": 65536,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 256,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15764,
"zero_count_experts": 616,
"active_ratio": 0.9623931623931624,
"min_count": 0,
"p05_count": 2.0,
"p10_count": 633.0,
"median_count": 6090.0,
"max_count": 131072,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 384,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15779,
"zero_count_experts": 601,
"active_ratio": 0.9633089133089133,
"min_count": 0,
"p05_count": 3.0,
"p10_count": 905.0,
"median_count": 8991.0,
"max_count": 196608,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 512,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15836,
"zero_count_experts": 544,
"active_ratio": 0.9667887667887668,
"min_count": 0,
"p05_count": 4.0,
"p10_count": 1208.7000000000012,
"median_count": 11901.0,
"max_count": 262144,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 640,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15854,
"zero_count_experts": 526,
"active_ratio": 0.9678876678876679,
"min_count": 0,
"p05_count": 6.0,
"p10_count": 1486.6000000000004,
"median_count": 14829.0,
"max_count": 327680,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 768,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15866,
"zero_count_experts": 514,
"active_ratio": 0.9686202686202686,
"min_count": 0,
"p05_count": 6.0,
"p10_count": 1767.4000000000005,
"median_count": 17887.0,
"max_count": 393216,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 896,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15874,
"zero_count_experts": 506,
"active_ratio": 0.9691086691086691,
"min_count": 0,
"p05_count": 7.0,
"p10_count": 2054.3000000000015,
"median_count": 20931.0,
"max_count": 458752,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 1024,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15883,
"zero_count_experts": 497,
"active_ratio": 0.9696581196581197,
"min_count": 0,
"p05_count": 8.0,
"p10_count": 2428.900000000001,
"median_count": 23935.0,
"max_count": 524288,
"min_required_count": 16,
"required_percentile": 5
}
}
]
},
"expert_coverage": {
"has_expert_counts": true,
"expert_modules": 180,
"total_experts": 16380,
"active_experts": 15883,
"zero_count_experts": 497,
"active_ratio": 0.9696581196581197,
"min_count": 0,
"p05_count": 8.0,
"p10_count": 2428.900000000001,
"median_count": 23935.0,
"max_count": 524288,
"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.gate_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.gate_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_experts.down_proj",
"model.layers.10.mlp.shared_experts.gate_proj",
"model.layers.10.mlp.shared_experts.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.gate_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_experts",
"model.layers.10.self_attn.v_router",
"model.layers.11.mlp.shared_experts.down_proj",
"model.layers.11.mlp.shared_experts.gate_proj",
"model.layers.11.mlp.shared_experts.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.gate_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_experts",
"model.layers.11.self_attn.v_router",
"model.layers.12.mlp.shared_experts.down_proj",
"model.layers.12.mlp.shared_experts.gate_proj",
"model.layers.12.mlp.shared_experts.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.gate_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_experts",
"model.layers.12.self_attn.v_router",
"model.layers.13.mlp.shared_experts.down_proj",
"model.layers.13.mlp.shared_experts.gate_proj",
"model.layers.13.mlp.shared_experts.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.gate_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_experts",
"model.layers.13.self_attn.v_router",
"model.layers.14.mlp.shared_experts.down_proj",
"model.layers.14.mlp.shared_experts.gate_proj",
"model.layers.14.mlp.shared_experts.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.gate_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_experts",
"model.layers.14.self_attn.v_router",
"model.layers.15.mlp.shared_experts.down_proj",
"model.layers.15.mlp.shared_experts.gate_proj",
"model.layers.15.mlp.shared_experts.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.gate_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_experts",
"model.layers.15.self_attn.v_router",
"model.layers.16.mlp.shared_experts.down_proj",
"model.layers.16.mlp.shared_experts.gate_proj",
"model.layers.16.mlp.shared_experts.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.gate_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_experts",
"model.layers.16.self_attn.v_router",
"model.layers.17.mlp.shared_experts.down_proj",
"model.layers.17.mlp.shared_experts.gate_proj",
"model.layers.17.mlp.shared_experts.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.gate_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_experts",
"model.layers.17.self_attn.v_router",
"model.layers.18.mlp.shared_experts.down_proj",
"model.layers.18.mlp.shared_experts.gate_proj",
"model.layers.18.mlp.shared_experts.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.gate_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_experts",
"model.layers.18.self_attn.v_router",
"model.layers.19.mlp.shared_experts.down_proj",
"model.layers.19.mlp.shared_experts.gate_proj",
"model.layers.19.mlp.shared_experts.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.gate_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_experts",
"model.layers.19.self_attn.v_router",
"model.layers.2.mlp.down_proj",
"model.layers.2.mlp.gate_proj",
"model.layers.2.mlp.up_proj",
"model.layers.2.self_attn.gate_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_experts.down_proj",
"model.layers.20.mlp.shared_experts.gate_proj",
"model.layers.20.mlp.shared_experts.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.gate_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_experts",
"model.layers.20.self_attn.v_router",
"model.layers.21.mlp.shared_experts.down_proj",
"model.layers.21.mlp.shared_experts.gate_proj",
"model.layers.21.mlp.shared_experts.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.gate_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_experts",
"model.layers.21.self_attn.v_router",
"model.layers.22.mlp.shared_experts.down_proj",
"model.layers.22.mlp.shared_experts.gate_proj",
"model.layers.22.mlp.shared_experts.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.gate_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_experts",
"model.layers.22.self_attn.v_router",
"model.layers.23.mlp.shared_experts.down_proj",
"model.layers.23.mlp.shared_experts.gate_proj",
"model.layers.23.mlp.shared_experts.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.gate_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_experts",
"model.layers.23.self_attn.v_router",
"model.layers.24.mlp.shared_experts.down_proj",
"model.layers.24.mlp.shared_experts.gate_proj",
"model.layers.24.mlp.shared_experts.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.gate_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_experts",
"model.layers.24.self_attn.v_router",
"model.layers.25.mlp.shared_experts.down_proj",
"model.layers.25.mlp.shared_experts.gate_proj",
"model.layers.25.mlp.shared_experts.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.gate_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_experts",
"model.layers.25.self_attn.v_router",
"model.layers.26.mlp.shared_experts.down_proj",
"model.layers.26.mlp.shared_experts.gate_proj",
"model.layers.26.mlp.shared_experts.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.gate_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_experts",
"model.layers.26.self_attn.v_router",
"model.layers.27.mlp.shared_experts.down_proj",
"model.layers.27.mlp.shared_experts.gate_proj",
"model.layers.27.mlp.shared_experts.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.gate_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_experts",
"model.layers.27.self_attn.v_router",
"model.layers.28.mlp.shared_experts.down_proj",
"model.layers.28.mlp.shared_experts.gate_proj",
"model.layers.28.mlp.shared_experts.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.gate_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_experts",
"model.layers.28.self_attn.v_router",
"model.layers.29.mlp.shared_experts.down_proj",
"model.layers.29.mlp.shared_experts.gate_proj",
"model.layers.29.mlp.shared_experts.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.gate_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_experts",
"model.layers.29.self_attn.v_router",
"model.layers.3.mlp.shared_experts.down_proj",
"model.layers.3.mlp.shared_experts.gate_proj",
"model.layers.3.mlp.shared_experts.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.gate_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_experts",
"model.layers.3.self_attn.v_router",
"model.layers.30.mlp.shared_experts.down_proj",
"model.layers.30.mlp.shared_experts.gate_proj",
"model.layers.30.mlp.shared_experts.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.gate_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_experts",
"model.layers.30.self_attn.v_router",
"model.layers.31.mlp.shared_experts.down_proj",
"model.layers.31.mlp.shared_experts.gate_proj",
"model.layers.31.mlp.shared_experts.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.gate_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_experts",
"model.layers.31.self_attn.v_router",
"model.layers.32.mlp.shared_experts.down_proj",
"model.layers.32.mlp.shared_experts.gate_proj",
"model.layers.32.mlp.shared_experts.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.gate_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_experts",
"model.layers.32.self_attn.v_router",
"model.layers.33.mlp.shared_experts.down_proj",
"model.layers.33.mlp.shared_experts.gate_proj",
"model.layers.33.mlp.shared_experts.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.gate_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_experts",
"model.layers.33.self_attn.v_router",
"model.layers.34.mlp.shared_experts.down_proj",
"model.layers.34.mlp.shared_experts.gate_proj",
"model.layers.34.mlp.shared_experts.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.gate_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_experts",
"model.layers.34.self_attn.v_router",
"model.layers.35.mlp.shared_experts.down_proj",
"model.layers.35.mlp.shared_experts.gate_proj",
"model.layers.35.mlp.shared_experts.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.gate_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_experts",
"model.layers.35.self_attn.v_router",
"model.layers.36.mlp.shared_experts.down_proj",
"model.layers.36.mlp.shared_experts.gate_proj",
"model.layers.36.mlp.shared_experts.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.gate_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_experts",
"model.layers.36.self_attn.v_router",
"model.layers.37.mlp.shared_experts.down_proj",
"model.layers.37.mlp.shared_experts.gate_proj",
"model.layers.37.mlp.shared_experts.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.gate_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_experts",
"model.layers.37.self_attn.v_router",
"model.layers.38.mlp.shared_experts.down_proj",
"model.layers.38.mlp.shared_experts.gate_proj",
"model.layers.38.mlp.shared_experts.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.gate_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_experts",
"model.layers.38.self_attn.v_router",
"model.layers.39.mlp.shared_experts.down_proj",
"model.layers.39.mlp.shared_experts.gate_proj",
"model.layers.39.mlp.shared_experts.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.gate_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_experts",
"model.layers.39.self_attn.v_router",
"model.layers.4.mlp.shared_experts.down_proj",
"model.layers.4.mlp.shared_experts.gate_proj",
"model.layers.4.mlp.shared_experts.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.gate_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_experts",
"model.layers.4.self_attn.v_router",
"model.layers.40.mlp.shared_experts.down_proj",
"model.layers.40.mlp.shared_experts.gate_proj",
"model.layers.40.mlp.shared_experts.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.gate_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_experts",
"model.layers.40.self_attn.v_router",
"model.layers.41.mlp.shared_experts.down_proj",
"model.layers.41.mlp.shared_experts.gate_proj",
"model.layers.41.mlp.shared_experts.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.gate_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_experts",
"model.layers.41.self_attn.v_router",
"model.layers.42.mlp.shared_experts.down_proj",
"model.layers.42.mlp.shared_experts.gate_proj",
"model.layers.42.mlp.shared_experts.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.gate_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_experts",
"model.layers.42.self_attn.v_router",
"model.layers.43.mlp.shared_experts.down_proj",
"model.layers.43.mlp.shared_experts.gate_proj",
"model.layers.43.mlp.shared_experts.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.gate_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_experts",
"model.layers.43.self_attn.v_router",
"model.layers.44.mlp.shared_experts.down_proj",
"model.layers.44.mlp.shared_experts.gate_proj",
"model.layers.44.mlp.shared_experts.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.gate_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_experts",
"model.layers.44.self_attn.v_router",
"model.layers.45.mlp.shared_experts.down_proj",
"model.layers.45.mlp.shared_experts.gate_proj",
"model.layers.45.mlp.shared_experts.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.gate_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_experts",
"model.layers.45.self_attn.v_router",
"model.layers.46.mlp.shared_experts.down_proj",
"model.layers.46.mlp.shared_experts.gate_proj",
"model.layers.46.mlp.shared_experts.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.gate_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_experts",
"model.layers.46.self_attn.v_router",
"model.layers.47.mlp.shared_experts.down_proj",
"model.layers.47.mlp.shared_experts.gate_proj",
"model.layers.47.mlp.shared_experts.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.gate_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_experts",
"model.layers.47.self_attn.v_router",
"model.layers.5.mlp.shared_experts.down_proj",
"model.layers.5.mlp.shared_experts.gate_proj",
"model.layers.5.mlp.shared_experts.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.gate_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_experts",
"model.layers.5.self_attn.v_router",
"model.layers.6.mlp.shared_experts.down_proj",
"model.layers.6.mlp.shared_experts.gate_proj",
"model.layers.6.mlp.shared_experts.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.gate_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_experts",
"model.layers.6.self_attn.v_router",
"model.layers.7.mlp.shared_experts.down_proj",
"model.layers.7.mlp.shared_experts.gate_proj",
"model.layers.7.mlp.shared_experts.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.gate_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_experts",
"model.layers.7.self_attn.v_router",
"model.layers.8.mlp.shared_experts.down_proj",
"model.layers.8.mlp.shared_experts.gate_proj",
"model.layers.8.mlp.shared_experts.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.gate_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_experts",
"model.layers.8.self_attn.v_router",
"model.layers.9.mlp.shared_experts.down_proj",
"model.layers.9.mlp.shared_experts.gate_proj",
"model.layers.9.mlp.shared_experts.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.gate_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_experts",
"model.layers.9.self_attn.v_router"
],
"missing": [
"lm_head"
],
"mismatched": [],
"zero_count_experts": 497
}