OvisOCR2-oQ6e / oq_imatrix_report.json
yugeshkarunamurthy's picture
Upload folder using huggingface_hub
5169481 verified
Raw
History Blame Contribute Delete
12.9 kB
{
"enabled": true,
"cache_path": "/Users/yugeshk/.one/models/.oqe_imatrix/OvisOCR2-30535413f70e-s128-l512.npz",
"cache_reused": false,
"entry_count": 186,
"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": 2097152,
"capture_budget_bytes": 134217728,
"system_available_bytes": 8290926592,
"metal_available_bytes": 12708779922,
"live_available_bytes": 8290926592,
"hidden_size": 1024,
"num_experts": 0,
"top_k": 1
},
"processed_samples": 128,
"installed_modules": 236,
"capture_module_classes": {
"Linear": 236
},
"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.linear_attn.in_proj_a",
"language_model.model.layers.0.linear_attn.in_proj_b",
"language_model.model.layers.0.linear_attn.in_proj_qkv",
"language_model.model.layers.0.linear_attn.in_proj_z",
"language_model.model.layers.0.linear_attn.out_proj",
"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.1.linear_attn.in_proj_a",
"language_model.model.layers.1.linear_attn.in_proj_b",
"language_model.model.layers.1.linear_attn.in_proj_qkv",
"language_model.model.layers.1.linear_attn.in_proj_z",
"language_model.model.layers.1.linear_attn.out_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.10.linear_attn.in_proj_a",
"language_model.model.layers.10.linear_attn.in_proj_b",
"language_model.model.layers.10.linear_attn.in_proj_qkv",
"language_model.model.layers.10.linear_attn.in_proj_z",
"language_model.model.layers.10.linear_attn.out_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.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.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.linear_attn.in_proj_a",
"language_model.model.layers.12.linear_attn.in_proj_b",
"language_model.model.layers.12.linear_attn.in_proj_qkv",
"language_model.model.layers.12.linear_attn.in_proj_z",
"language_model.model.layers.12.linear_attn.out_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.13.linear_attn.in_proj_a",
"language_model.model.layers.13.linear_attn.in_proj_b",
"language_model.model.layers.13.linear_attn.in_proj_qkv",
"language_model.model.layers.13.linear_attn.in_proj_z",
"language_model.model.layers.13.linear_attn.out_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.14.linear_attn.in_proj_a",
"language_model.model.layers.14.linear_attn.in_proj_b",
"language_model.model.layers.14.linear_attn.in_proj_qkv",
"language_model.model.layers.14.linear_attn.in_proj_z",
"language_model.model.layers.14.linear_attn.out_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.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.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.linear_attn.in_proj_a",
"language_model.model.layers.16.linear_attn.in_proj_b",
"language_model.model.layers.16.linear_attn.in_proj_qkv",
"language_model.model.layers.16.linear_attn.in_proj_z",
"language_model.model.layers.16.linear_attn.out_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.17.linear_attn.in_proj_a",
"language_model.model.layers.17.linear_attn.in_proj_b",
"language_model.model.layers.17.linear_attn.in_proj_qkv",
"language_model.model.layers.17.linear_attn.in_proj_z",
"language_model.model.layers.17.linear_attn.out_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.18.linear_attn.in_proj_a",
"language_model.model.layers.18.linear_attn.in_proj_b",
"language_model.model.layers.18.linear_attn.in_proj_qkv",
"language_model.model.layers.18.linear_attn.in_proj_z",
"language_model.model.layers.18.linear_attn.out_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.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.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.linear_attn.in_proj_a",
"language_model.model.layers.2.linear_attn.in_proj_b",
"language_model.model.layers.2.linear_attn.in_proj_qkv",
"language_model.model.layers.2.linear_attn.in_proj_z",
"language_model.model.layers.2.linear_attn.out_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.20.linear_attn.in_proj_a",
"language_model.model.layers.20.linear_attn.in_proj_b",
"language_model.model.layers.20.linear_attn.in_proj_qkv",
"language_model.model.layers.20.linear_attn.in_proj_z",
"language_model.model.layers.20.linear_attn.out_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.21.linear_attn.in_proj_a",
"language_model.model.layers.21.linear_attn.in_proj_b",
"language_model.model.layers.21.linear_attn.in_proj_qkv",
"language_model.model.layers.21.linear_attn.in_proj_z",
"language_model.model.layers.21.linear_attn.out_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.22.linear_attn.in_proj_a",
"language_model.model.layers.22.linear_attn.in_proj_b",
"language_model.model.layers.22.linear_attn.in_proj_qkv",
"language_model.model.layers.22.linear_attn.in_proj_z",
"language_model.model.layers.22.linear_attn.out_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.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.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.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.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.4.linear_attn.in_proj_a",
"language_model.model.layers.4.linear_attn.in_proj_b",
"language_model.model.layers.4.linear_attn.in_proj_qkv",
"language_model.model.layers.4.linear_attn.in_proj_z",
"language_model.model.layers.4.linear_attn.out_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.5.linear_attn.in_proj_a",
"language_model.model.layers.5.linear_attn.in_proj_b",
"language_model.model.layers.5.linear_attn.in_proj_qkv",
"language_model.model.layers.5.linear_attn.in_proj_z",
"language_model.model.layers.5.linear_attn.out_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.6.linear_attn.in_proj_a",
"language_model.model.layers.6.linear_attn.in_proj_b",
"language_model.model.layers.6.linear_attn.in_proj_qkv",
"language_model.model.layers.6.linear_attn.in_proj_z",
"language_model.model.layers.6.linear_attn.out_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.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.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.linear_attn.in_proj_a",
"language_model.model.layers.8.linear_attn.in_proj_b",
"language_model.model.layers.8.linear_attn.in_proj_qkv",
"language_model.model.layers.8.linear_attn.in_proj_z",
"language_model.model.layers.8.linear_attn.out_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.9.linear_attn.in_proj_a",
"language_model.model.layers.9.linear_attn.in_proj_b",
"language_model.model.layers.9.linear_attn.in_proj_qkv",
"language_model.model.layers.9.linear_attn.in_proj_z",
"language_model.model.layers.9.linear_attn.out_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"
],
"missing": [
"language_model.model.embed_tokens"
],
"mismatched": [],
"zero_count_experts": 0
}