Laguna-S-2.1-oQ5e / oq_imatrix_report.json
gabfssilva's picture
Upload folder using huggingface_hub
2f389f3 verified
Raw
History Blame
38.3 kB
{
"enabled": true,
"cache_path": "/Users/gabfssilva/.cache/huggingface/hub/models--local--Laguna-S-2.1-mlx-oQ4e-gs128/snapshots/.oqe_imatrix/e4daa58f75dbe26f54af634b276e69336beec443-oQe-s128-l512.npz",
"cache_reused": false,
"entry_count": 572,
"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": 88,
"batch_plan": {
"micro_batch_size": 12,
"estimated_sample_bytes": 62914560,
"capture_budget_bytes": 805306368,
"system_available_bytes": 112778838016,
"metal_available_bytes": 115443563072,
"live_available_bytes": 112778838016,
"hidden_size": 3072,
"num_experts": 256,
"top_k": 10
},
"processed_samples": 1024,
"installed_modules": 573,
"capture_module_classes": {
"Linear": 47,
"QuantizedLinear": 385,
"QuantizedSwitchLinear": 141
},
"switch_capture_modules": 141,
"requires_expert_counts": true,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36084,
"zero_count_experts": 12,
"active_ratio": 0.9996675531914894,
"min_count": 0,
"p05_count": 2965.0,
"p10_count": 4486.0,
"median_count": 14013.5,
"max_count": 313406,
"min_required_count": 16,
"required_percentile": 5
},
"rounds": [
{
"processed_samples": 128,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36057,
"zero_count_experts": 39,
"active_ratio": 0.9989195478723404,
"min_count": 0,
"p05_count": 370.0,
"p10_count": 570.0,
"median_count": 1753.0,
"max_count": 38297,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 256,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36066,
"zero_count_experts": 30,
"active_ratio": 0.9991688829787234,
"min_count": 0,
"p05_count": 690.0,
"p10_count": 1064.0,
"median_count": 3447.0,
"max_count": 80166,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 384,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36078,
"zero_count_experts": 18,
"active_ratio": 0.999501329787234,
"min_count": 0,
"p05_count": 1049.0,
"p10_count": 1617.0,
"median_count": 5190.5,
"max_count": 120096,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 512,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36078,
"zero_count_experts": 18,
"active_ratio": 0.999501329787234,
"min_count": 0,
"p05_count": 1439.0,
"p10_count": 2209.0,
"median_count": 6954.5,
"max_count": 158827,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 640,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36081,
"zero_count_experts": 15,
"active_ratio": 0.9995844414893617,
"min_count": 0,
"p05_count": 1839.0,
"p10_count": 2810.0,
"median_count": 8751.0,
"max_count": 196661,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 768,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36081,
"zero_count_experts": 15,
"active_ratio": 0.9995844414893617,
"min_count": 0,
"p05_count": 2244.0,
"p10_count": 3404.0,
"median_count": 10535.5,
"max_count": 233382,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 896,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36081,
"zero_count_experts": 15,
"active_ratio": 0.9995844414893617,
"min_count": 0,
"p05_count": 2627.0,
"p10_count": 3972.0,
"median_count": 12280.5,
"max_count": 273279,
"min_required_count": 16,
"required_percentile": 5
}
},
{
"processed_samples": 1024,
"coverage_sufficient": false,
"collection_sufficient": false,
"coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36084,
"zero_count_experts": 12,
"active_ratio": 0.9996675531914894,
"min_count": 0,
"p05_count": 2965.0,
"p10_count": 4486.0,
"median_count": 14013.5,
"max_count": 313406,
"min_required_count": 16,
"required_percentile": 5
}
}
]
},
"expert_coverage": {
"has_expert_counts": true,
"expert_modules": 141,
"total_experts": 36096,
"active_experts": 36084,
"zero_count_experts": 12,
"active_ratio": 0.9996675531914894,
"min_count": 0,
"p05_count": 2965.0,
"p10_count": 4486.0,
"median_count": 14013.5,
"max_count": 313406,
"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.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.1.mlp.shared_expert.gate_proj",
"language_model.model.layers.1.mlp.shared_expert.up_proj",
"language_model.model.layers.1.mlp.switch_mlp.down_proj",
"language_model.model.layers.1.mlp.switch_mlp.gate_proj",
"language_model.model.layers.1.mlp.switch_mlp.up_proj",
"language_model.model.layers.1.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.10.mlp.shared_expert.gate_proj",
"language_model.model.layers.10.mlp.shared_expert.up_proj",
"language_model.model.layers.10.mlp.switch_mlp.down_proj",
"language_model.model.layers.10.mlp.switch_mlp.gate_proj",
"language_model.model.layers.10.mlp.switch_mlp.up_proj",
"language_model.model.layers.10.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.11.mlp.shared_expert.gate_proj",
"language_model.model.layers.11.mlp.shared_expert.up_proj",
"language_model.model.layers.11.mlp.switch_mlp.down_proj",
"language_model.model.layers.11.mlp.switch_mlp.gate_proj",
"language_model.model.layers.11.mlp.switch_mlp.up_proj",
"language_model.model.layers.11.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.12.mlp.shared_expert.gate_proj",
"language_model.model.layers.12.mlp.shared_expert.up_proj",
"language_model.model.layers.12.mlp.switch_mlp.down_proj",
"language_model.model.layers.12.mlp.switch_mlp.gate_proj",
"language_model.model.layers.12.mlp.switch_mlp.up_proj",
"language_model.model.layers.12.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.13.mlp.shared_expert.gate_proj",
"language_model.model.layers.13.mlp.shared_expert.up_proj",
"language_model.model.layers.13.mlp.switch_mlp.down_proj",
"language_model.model.layers.13.mlp.switch_mlp.gate_proj",
"language_model.model.layers.13.mlp.switch_mlp.up_proj",
"language_model.model.layers.13.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.14.mlp.shared_expert.gate_proj",
"language_model.model.layers.14.mlp.shared_expert.up_proj",
"language_model.model.layers.14.mlp.switch_mlp.down_proj",
"language_model.model.layers.14.mlp.switch_mlp.gate_proj",
"language_model.model.layers.14.mlp.switch_mlp.up_proj",
"language_model.model.layers.14.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.15.mlp.shared_expert.gate_proj",
"language_model.model.layers.15.mlp.shared_expert.up_proj",
"language_model.model.layers.15.mlp.switch_mlp.down_proj",
"language_model.model.layers.15.mlp.switch_mlp.gate_proj",
"language_model.model.layers.15.mlp.switch_mlp.up_proj",
"language_model.model.layers.15.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.16.mlp.shared_expert.gate_proj",
"language_model.model.layers.16.mlp.shared_expert.up_proj",
"language_model.model.layers.16.mlp.switch_mlp.down_proj",
"language_model.model.layers.16.mlp.switch_mlp.gate_proj",
"language_model.model.layers.16.mlp.switch_mlp.up_proj",
"language_model.model.layers.16.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.17.mlp.shared_expert.gate_proj",
"language_model.model.layers.17.mlp.shared_expert.up_proj",
"language_model.model.layers.17.mlp.switch_mlp.down_proj",
"language_model.model.layers.17.mlp.switch_mlp.gate_proj",
"language_model.model.layers.17.mlp.switch_mlp.up_proj",
"language_model.model.layers.17.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.18.mlp.shared_expert.gate_proj",
"language_model.model.layers.18.mlp.shared_expert.up_proj",
"language_model.model.layers.18.mlp.switch_mlp.down_proj",
"language_model.model.layers.18.mlp.switch_mlp.gate_proj",
"language_model.model.layers.18.mlp.switch_mlp.up_proj",
"language_model.model.layers.18.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.19.mlp.shared_expert.gate_proj",
"language_model.model.layers.19.mlp.shared_expert.up_proj",
"language_model.model.layers.19.mlp.switch_mlp.down_proj",
"language_model.model.layers.19.mlp.switch_mlp.gate_proj",
"language_model.model.layers.19.mlp.switch_mlp.up_proj",
"language_model.model.layers.19.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.2.mlp.shared_expert.gate_proj",
"language_model.model.layers.2.mlp.shared_expert.up_proj",
"language_model.model.layers.2.mlp.switch_mlp.down_proj",
"language_model.model.layers.2.mlp.switch_mlp.gate_proj",
"language_model.model.layers.2.mlp.switch_mlp.up_proj",
"language_model.model.layers.2.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.20.mlp.shared_expert.gate_proj",
"language_model.model.layers.20.mlp.shared_expert.up_proj",
"language_model.model.layers.20.mlp.switch_mlp.down_proj",
"language_model.model.layers.20.mlp.switch_mlp.gate_proj",
"language_model.model.layers.20.mlp.switch_mlp.up_proj",
"language_model.model.layers.20.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.21.mlp.shared_expert.gate_proj",
"language_model.model.layers.21.mlp.shared_expert.up_proj",
"language_model.model.layers.21.mlp.switch_mlp.down_proj",
"language_model.model.layers.21.mlp.switch_mlp.gate_proj",
"language_model.model.layers.21.mlp.switch_mlp.up_proj",
"language_model.model.layers.21.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.22.mlp.shared_expert.gate_proj",
"language_model.model.layers.22.mlp.shared_expert.up_proj",
"language_model.model.layers.22.mlp.switch_mlp.down_proj",
"language_model.model.layers.22.mlp.switch_mlp.gate_proj",
"language_model.model.layers.22.mlp.switch_mlp.up_proj",
"language_model.model.layers.22.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.23.mlp.shared_expert.gate_proj",
"language_model.model.layers.23.mlp.shared_expert.up_proj",
"language_model.model.layers.23.mlp.switch_mlp.down_proj",
"language_model.model.layers.23.mlp.switch_mlp.gate_proj",
"language_model.model.layers.23.mlp.switch_mlp.up_proj",
"language_model.model.layers.23.self_attn.g_proj",
"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.mlp.shared_expert.down_proj",
"language_model.model.layers.24.mlp.shared_expert.gate_proj",
"language_model.model.layers.24.mlp.shared_expert.up_proj",
"language_model.model.layers.24.mlp.switch_mlp.down_proj",
"language_model.model.layers.24.mlp.switch_mlp.gate_proj",
"language_model.model.layers.24.mlp.switch_mlp.up_proj",
"language_model.model.layers.24.self_attn.g_proj",
"language_model.model.layers.24.self_attn.k_proj",
"language_model.model.layers.24.self_attn.o_proj",
"language_model.model.layers.24.self_attn.q_proj",
"language_model.model.layers.24.self_attn.v_proj",
"language_model.model.layers.25.mlp.shared_expert.down_proj",
"language_model.model.layers.25.mlp.shared_expert.gate_proj",
"language_model.model.layers.25.mlp.shared_expert.up_proj",
"language_model.model.layers.25.mlp.switch_mlp.down_proj",
"language_model.model.layers.25.mlp.switch_mlp.gate_proj",
"language_model.model.layers.25.mlp.switch_mlp.up_proj",
"language_model.model.layers.25.self_attn.g_proj",
"language_model.model.layers.25.self_attn.k_proj",
"language_model.model.layers.25.self_attn.o_proj",
"language_model.model.layers.25.self_attn.q_proj",
"language_model.model.layers.25.self_attn.v_proj",
"language_model.model.layers.26.mlp.shared_expert.down_proj",
"language_model.model.layers.26.mlp.shared_expert.gate_proj",
"language_model.model.layers.26.mlp.shared_expert.up_proj",
"language_model.model.layers.26.mlp.switch_mlp.down_proj",
"language_model.model.layers.26.mlp.switch_mlp.gate_proj",
"language_model.model.layers.26.mlp.switch_mlp.up_proj",
"language_model.model.layers.26.self_attn.g_proj",
"language_model.model.layers.26.self_attn.k_proj",
"language_model.model.layers.26.self_attn.o_proj",
"language_model.model.layers.26.self_attn.q_proj",
"language_model.model.layers.26.self_attn.v_proj",
"language_model.model.layers.27.mlp.shared_expert.down_proj",
"language_model.model.layers.27.mlp.shared_expert.gate_proj",
"language_model.model.layers.27.mlp.shared_expert.up_proj",
"language_model.model.layers.27.mlp.switch_mlp.down_proj",
"language_model.model.layers.27.mlp.switch_mlp.gate_proj",
"language_model.model.layers.27.mlp.switch_mlp.up_proj",
"language_model.model.layers.27.self_attn.g_proj",
"language_model.model.layers.27.self_attn.k_proj",
"language_model.model.layers.27.self_attn.o_proj",
"language_model.model.layers.27.self_attn.q_proj",
"language_model.model.layers.27.self_attn.v_proj",
"language_model.model.layers.28.mlp.shared_expert.down_proj",
"language_model.model.layers.28.mlp.shared_expert.gate_proj",
"language_model.model.layers.28.mlp.shared_expert.up_proj",
"language_model.model.layers.28.mlp.switch_mlp.down_proj",
"language_model.model.layers.28.mlp.switch_mlp.gate_proj",
"language_model.model.layers.28.mlp.switch_mlp.up_proj",
"language_model.model.layers.28.self_attn.g_proj",
"language_model.model.layers.28.self_attn.k_proj",
"language_model.model.layers.28.self_attn.o_proj",
"language_model.model.layers.28.self_attn.q_proj",
"language_model.model.layers.28.self_attn.v_proj",
"language_model.model.layers.29.mlp.shared_expert.down_proj",
"language_model.model.layers.29.mlp.shared_expert.gate_proj",
"language_model.model.layers.29.mlp.shared_expert.up_proj",
"language_model.model.layers.29.mlp.switch_mlp.down_proj",
"language_model.model.layers.29.mlp.switch_mlp.gate_proj",
"language_model.model.layers.29.mlp.switch_mlp.up_proj",
"language_model.model.layers.29.self_attn.g_proj",
"language_model.model.layers.29.self_attn.k_proj",
"language_model.model.layers.29.self_attn.o_proj",
"language_model.model.layers.29.self_attn.q_proj",
"language_model.model.layers.29.self_attn.v_proj",
"language_model.model.layers.3.mlp.shared_expert.down_proj",
"language_model.model.layers.3.mlp.shared_expert.gate_proj",
"language_model.model.layers.3.mlp.shared_expert.up_proj",
"language_model.model.layers.3.mlp.switch_mlp.down_proj",
"language_model.model.layers.3.mlp.switch_mlp.gate_proj",
"language_model.model.layers.3.mlp.switch_mlp.up_proj",
"language_model.model.layers.3.self_attn.g_proj",
"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.mlp.shared_expert.down_proj",
"language_model.model.layers.30.mlp.shared_expert.gate_proj",
"language_model.model.layers.30.mlp.shared_expert.up_proj",
"language_model.model.layers.30.mlp.switch_mlp.down_proj",
"language_model.model.layers.30.mlp.switch_mlp.gate_proj",
"language_model.model.layers.30.mlp.switch_mlp.up_proj",
"language_model.model.layers.30.self_attn.g_proj",
"language_model.model.layers.30.self_attn.k_proj",
"language_model.model.layers.30.self_attn.o_proj",
"language_model.model.layers.30.self_attn.q_proj",
"language_model.model.layers.30.self_attn.v_proj",
"language_model.model.layers.31.mlp.shared_expert.down_proj",
"language_model.model.layers.31.mlp.shared_expert.gate_proj",
"language_model.model.layers.31.mlp.shared_expert.up_proj",
"language_model.model.layers.31.mlp.switch_mlp.down_proj",
"language_model.model.layers.31.mlp.switch_mlp.gate_proj",
"language_model.model.layers.31.mlp.switch_mlp.up_proj",
"language_model.model.layers.31.self_attn.g_proj",
"language_model.model.layers.31.self_attn.k_proj",
"language_model.model.layers.31.self_attn.o_proj",
"language_model.model.layers.31.self_attn.q_proj",
"language_model.model.layers.31.self_attn.v_proj",
"language_model.model.layers.32.mlp.shared_expert.down_proj",
"language_model.model.layers.32.mlp.shared_expert.gate_proj",
"language_model.model.layers.32.mlp.shared_expert.up_proj",
"language_model.model.layers.32.mlp.switch_mlp.down_proj",
"language_model.model.layers.32.mlp.switch_mlp.gate_proj",
"language_model.model.layers.32.mlp.switch_mlp.up_proj",
"language_model.model.layers.32.self_attn.g_proj",
"language_model.model.layers.32.self_attn.k_proj",
"language_model.model.layers.32.self_attn.o_proj",
"language_model.model.layers.32.self_attn.q_proj",
"language_model.model.layers.32.self_attn.v_proj",
"language_model.model.layers.33.mlp.shared_expert.down_proj",
"language_model.model.layers.33.mlp.shared_expert.gate_proj",
"language_model.model.layers.33.mlp.shared_expert.up_proj",
"language_model.model.layers.33.mlp.switch_mlp.down_proj",
"language_model.model.layers.33.mlp.switch_mlp.gate_proj",
"language_model.model.layers.33.mlp.switch_mlp.up_proj",
"language_model.model.layers.33.self_attn.g_proj",
"language_model.model.layers.33.self_attn.k_proj",
"language_model.model.layers.33.self_attn.o_proj",
"language_model.model.layers.33.self_attn.q_proj",
"language_model.model.layers.33.self_attn.v_proj",
"language_model.model.layers.34.mlp.shared_expert.down_proj",
"language_model.model.layers.34.mlp.shared_expert.gate_proj",
"language_model.model.layers.34.mlp.shared_expert.up_proj",
"language_model.model.layers.34.mlp.switch_mlp.down_proj",
"language_model.model.layers.34.mlp.switch_mlp.gate_proj",
"language_model.model.layers.34.mlp.switch_mlp.up_proj",
"language_model.model.layers.34.self_attn.g_proj",
"language_model.model.layers.34.self_attn.k_proj",
"language_model.model.layers.34.self_attn.o_proj",
"language_model.model.layers.34.self_attn.q_proj",
"language_model.model.layers.34.self_attn.v_proj",
"language_model.model.layers.35.mlp.shared_expert.down_proj",
"language_model.model.layers.35.mlp.shared_expert.gate_proj",
"language_model.model.layers.35.mlp.shared_expert.up_proj",
"language_model.model.layers.35.mlp.switch_mlp.down_proj",
"language_model.model.layers.35.mlp.switch_mlp.gate_proj",
"language_model.model.layers.35.mlp.switch_mlp.up_proj",
"language_model.model.layers.35.self_attn.g_proj",
"language_model.model.layers.35.self_attn.k_proj",
"language_model.model.layers.35.self_attn.o_proj",
"language_model.model.layers.35.self_attn.q_proj",
"language_model.model.layers.35.self_attn.v_proj",
"language_model.model.layers.36.mlp.shared_expert.down_proj",
"language_model.model.layers.36.mlp.shared_expert.gate_proj",
"language_model.model.layers.36.mlp.shared_expert.up_proj",
"language_model.model.layers.36.mlp.switch_mlp.down_proj",
"language_model.model.layers.36.mlp.switch_mlp.gate_proj",
"language_model.model.layers.36.mlp.switch_mlp.up_proj",
"language_model.model.layers.36.self_attn.g_proj",
"language_model.model.layers.36.self_attn.k_proj",
"language_model.model.layers.36.self_attn.o_proj",
"language_model.model.layers.36.self_attn.q_proj",
"language_model.model.layers.36.self_attn.v_proj",
"language_model.model.layers.37.mlp.shared_expert.down_proj",
"language_model.model.layers.37.mlp.shared_expert.gate_proj",
"language_model.model.layers.37.mlp.shared_expert.up_proj",
"language_model.model.layers.37.mlp.switch_mlp.down_proj",
"language_model.model.layers.37.mlp.switch_mlp.gate_proj",
"language_model.model.layers.37.mlp.switch_mlp.up_proj",
"language_model.model.layers.37.self_attn.g_proj",
"language_model.model.layers.37.self_attn.k_proj",
"language_model.model.layers.37.self_attn.o_proj",
"language_model.model.layers.37.self_attn.q_proj",
"language_model.model.layers.37.self_attn.v_proj",
"language_model.model.layers.38.mlp.shared_expert.down_proj",
"language_model.model.layers.38.mlp.shared_expert.gate_proj",
"language_model.model.layers.38.mlp.shared_expert.up_proj",
"language_model.model.layers.38.mlp.switch_mlp.down_proj",
"language_model.model.layers.38.mlp.switch_mlp.gate_proj",
"language_model.model.layers.38.mlp.switch_mlp.up_proj",
"language_model.model.layers.38.self_attn.g_proj",
"language_model.model.layers.38.self_attn.k_proj",
"language_model.model.layers.38.self_attn.o_proj",
"language_model.model.layers.38.self_attn.q_proj",
"language_model.model.layers.38.self_attn.v_proj",
"language_model.model.layers.39.mlp.shared_expert.down_proj",
"language_model.model.layers.39.mlp.shared_expert.gate_proj",
"language_model.model.layers.39.mlp.shared_expert.up_proj",
"language_model.model.layers.39.mlp.switch_mlp.down_proj",
"language_model.model.layers.39.mlp.switch_mlp.gate_proj",
"language_model.model.layers.39.mlp.switch_mlp.up_proj",
"language_model.model.layers.39.self_attn.g_proj",
"language_model.model.layers.39.self_attn.k_proj",
"language_model.model.layers.39.self_attn.o_proj",
"language_model.model.layers.39.self_attn.q_proj",
"language_model.model.layers.39.self_attn.v_proj",
"language_model.model.layers.4.mlp.shared_expert.down_proj",
"language_model.model.layers.4.mlp.shared_expert.gate_proj",
"language_model.model.layers.4.mlp.shared_expert.up_proj",
"language_model.model.layers.4.mlp.switch_mlp.down_proj",
"language_model.model.layers.4.mlp.switch_mlp.gate_proj",
"language_model.model.layers.4.mlp.switch_mlp.up_proj",
"language_model.model.layers.4.self_attn.g_proj",
"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.mlp.shared_expert.down_proj",
"language_model.model.layers.40.mlp.shared_expert.gate_proj",
"language_model.model.layers.40.mlp.shared_expert.up_proj",
"language_model.model.layers.40.mlp.switch_mlp.down_proj",
"language_model.model.layers.40.mlp.switch_mlp.gate_proj",
"language_model.model.layers.40.mlp.switch_mlp.up_proj",
"language_model.model.layers.40.self_attn.g_proj",
"language_model.model.layers.40.self_attn.k_proj",
"language_model.model.layers.40.self_attn.o_proj",
"language_model.model.layers.40.self_attn.q_proj",
"language_model.model.layers.40.self_attn.v_proj",
"language_model.model.layers.41.mlp.shared_expert.down_proj",
"language_model.model.layers.41.mlp.shared_expert.gate_proj",
"language_model.model.layers.41.mlp.shared_expert.up_proj",
"language_model.model.layers.41.mlp.switch_mlp.down_proj",
"language_model.model.layers.41.mlp.switch_mlp.gate_proj",
"language_model.model.layers.41.mlp.switch_mlp.up_proj",
"language_model.model.layers.41.self_attn.g_proj",
"language_model.model.layers.41.self_attn.k_proj",
"language_model.model.layers.41.self_attn.o_proj",
"language_model.model.layers.41.self_attn.q_proj",
"language_model.model.layers.41.self_attn.v_proj",
"language_model.model.layers.42.mlp.shared_expert.down_proj",
"language_model.model.layers.42.mlp.shared_expert.gate_proj",
"language_model.model.layers.42.mlp.shared_expert.up_proj",
"language_model.model.layers.42.mlp.switch_mlp.down_proj",
"language_model.model.layers.42.mlp.switch_mlp.gate_proj",
"language_model.model.layers.42.mlp.switch_mlp.up_proj",
"language_model.model.layers.42.self_attn.g_proj",
"language_model.model.layers.42.self_attn.k_proj",
"language_model.model.layers.42.self_attn.o_proj",
"language_model.model.layers.42.self_attn.q_proj",
"language_model.model.layers.42.self_attn.v_proj",
"language_model.model.layers.43.mlp.shared_expert.down_proj",
"language_model.model.layers.43.mlp.shared_expert.gate_proj",
"language_model.model.layers.43.mlp.shared_expert.up_proj",
"language_model.model.layers.43.mlp.switch_mlp.down_proj",
"language_model.model.layers.43.mlp.switch_mlp.gate_proj",
"language_model.model.layers.43.mlp.switch_mlp.up_proj",
"language_model.model.layers.43.self_attn.g_proj",
"language_model.model.layers.43.self_attn.k_proj",
"language_model.model.layers.43.self_attn.o_proj",
"language_model.model.layers.43.self_attn.q_proj",
"language_model.model.layers.43.self_attn.v_proj",
"language_model.model.layers.44.mlp.shared_expert.down_proj",
"language_model.model.layers.44.mlp.shared_expert.gate_proj",
"language_model.model.layers.44.mlp.shared_expert.up_proj",
"language_model.model.layers.44.mlp.switch_mlp.down_proj",
"language_model.model.layers.44.mlp.switch_mlp.gate_proj",
"language_model.model.layers.44.mlp.switch_mlp.up_proj",
"language_model.model.layers.44.self_attn.g_proj",
"language_model.model.layers.44.self_attn.k_proj",
"language_model.model.layers.44.self_attn.o_proj",
"language_model.model.layers.44.self_attn.q_proj",
"language_model.model.layers.44.self_attn.v_proj",
"language_model.model.layers.45.mlp.shared_expert.down_proj",
"language_model.model.layers.45.mlp.shared_expert.gate_proj",
"language_model.model.layers.45.mlp.shared_expert.up_proj",
"language_model.model.layers.45.mlp.switch_mlp.down_proj",
"language_model.model.layers.45.mlp.switch_mlp.gate_proj",
"language_model.model.layers.45.mlp.switch_mlp.up_proj",
"language_model.model.layers.45.self_attn.g_proj",
"language_model.model.layers.45.self_attn.k_proj",
"language_model.model.layers.45.self_attn.o_proj",
"language_model.model.layers.45.self_attn.q_proj",
"language_model.model.layers.45.self_attn.v_proj",
"language_model.model.layers.46.mlp.shared_expert.down_proj",
"language_model.model.layers.46.mlp.shared_expert.gate_proj",
"language_model.model.layers.46.mlp.shared_expert.up_proj",
"language_model.model.layers.46.mlp.switch_mlp.down_proj",
"language_model.model.layers.46.mlp.switch_mlp.gate_proj",
"language_model.model.layers.46.mlp.switch_mlp.up_proj",
"language_model.model.layers.46.self_attn.g_proj",
"language_model.model.layers.46.self_attn.k_proj",
"language_model.model.layers.46.self_attn.o_proj",
"language_model.model.layers.46.self_attn.q_proj",
"language_model.model.layers.46.self_attn.v_proj",
"language_model.model.layers.47.mlp.shared_expert.down_proj",
"language_model.model.layers.47.mlp.shared_expert.gate_proj",
"language_model.model.layers.47.mlp.shared_expert.up_proj",
"language_model.model.layers.47.mlp.switch_mlp.down_proj",
"language_model.model.layers.47.mlp.switch_mlp.gate_proj",
"language_model.model.layers.47.mlp.switch_mlp.up_proj",
"language_model.model.layers.47.self_attn.g_proj",
"language_model.model.layers.47.self_attn.k_proj",
"language_model.model.layers.47.self_attn.o_proj",
"language_model.model.layers.47.self_attn.q_proj",
"language_model.model.layers.47.self_attn.v_proj",
"language_model.model.layers.5.mlp.shared_expert.down_proj",
"language_model.model.layers.5.mlp.shared_expert.gate_proj",
"language_model.model.layers.5.mlp.shared_expert.up_proj",
"language_model.model.layers.5.mlp.switch_mlp.down_proj",
"language_model.model.layers.5.mlp.switch_mlp.gate_proj",
"language_model.model.layers.5.mlp.switch_mlp.up_proj",
"language_model.model.layers.5.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.6.mlp.shared_expert.gate_proj",
"language_model.model.layers.6.mlp.shared_expert.up_proj",
"language_model.model.layers.6.mlp.switch_mlp.down_proj",
"language_model.model.layers.6.mlp.switch_mlp.gate_proj",
"language_model.model.layers.6.mlp.switch_mlp.up_proj",
"language_model.model.layers.6.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.7.mlp.shared_expert.gate_proj",
"language_model.model.layers.7.mlp.shared_expert.up_proj",
"language_model.model.layers.7.mlp.switch_mlp.down_proj",
"language_model.model.layers.7.mlp.switch_mlp.gate_proj",
"language_model.model.layers.7.mlp.switch_mlp.up_proj",
"language_model.model.layers.7.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.8.mlp.shared_expert.gate_proj",
"language_model.model.layers.8.mlp.shared_expert.up_proj",
"language_model.model.layers.8.mlp.switch_mlp.down_proj",
"language_model.model.layers.8.mlp.switch_mlp.gate_proj",
"language_model.model.layers.8.mlp.switch_mlp.up_proj",
"language_model.model.layers.8.self_attn.g_proj",
"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.shared_expert.down_proj",
"language_model.model.layers.9.mlp.shared_expert.gate_proj",
"language_model.model.layers.9.mlp.shared_expert.up_proj",
"language_model.model.layers.9.mlp.switch_mlp.down_proj",
"language_model.model.layers.9.mlp.switch_mlp.gate_proj",
"language_model.model.layers.9.mlp.switch_mlp.up_proj",
"language_model.model.layers.9.self_attn.g_proj",
"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.lm_head",
"language_model.model.embed_tokens"
],
"mismatched": [],
"zero_count_experts": 12
}